inclusionAI

/

Ling-3.0-flash

like 326

Follow

inclusionAI 2.62k

https://huggingface.co/gopi87/Lingflashfixclaudecode/tree/main

i have manually fixed the issues with claude code

Thank you so much for your contribution! Since we don't currently provide official support for llama.cpp, testing under this framework hasn't been as thorough as we'd like. We truly appreciate your efforts in identifying and fixing the issue — we'll make sure to merge your fix when we release the corresponding version in the future. Thanks again for your help!

@gopi87 thank you!

I'm curious, how did you manage to use AI (Claude in this case) to fix a Jinja template without it stopping itself when outputting one of the stop tokens itself?

Sometimes I'll use Qwen to try to fix a Jinja template but when it comes across lets say </think> it stops reasoning because it thinks that token should stop its own chat.

@gopi87 thank you!

I'm curious, how did you manage to use AI (Claude in this case) to fix a Jinja template without it stopping itself when outputting one of the stop tokens itself?

Sometimes I'll use Qwen to try to fix a Jinja template but when it comes across lets say </think> it stops reasoning because it thinks that token should stop its own chat.

Much of the fixes on this stuff get's done using the frontier models (like Fable, or GPT 5.6 Sol), at least as far as I can tell anecdotally from seeing PRs. They don't use the same chat templates so parsing a </think> (or anything else that shows up in jinja templates) won't (souldnt) really take effect.

@gopi87 thank you!

I'm curious, how did you manage to use AI (Claude in this case) to fix a Jinja template without it stopping itself when outputting one of the stop tokens itself?

Sometimes I'll use Qwen to try to fix a Jinja template but when it comes across lets say </think> it stops reasoning because it thinks that token should stop its own chat.

hi i dont know what i did but iwas able to use the model in the claude code upto 150k but after that i am getting the "/n" the chat template i took it from here onguy did some modification then i used old qwen tepmlate as a model to fix it one sec i will add my template and the source where i get it from

@Kayook the person who fixed the temlate and you see everythink here https://huggingface.co/gopi87/Lingflashfixclaudecode

curently i am focusing on fix the "/n" repation after 150k context fill

Also had issues with "/n" spam and model hanging when trying to tool call
I went in different direction - i've seen people fix the tool call issue through modifying parser code in llamacpp, can be seen here - https://github.com/ggml-org/llama.cpp/pull/26608
So i've sent my local AI on a mission to reuse code for tool call parser issues + attempt to fix the /n spam at the same time. Currently its working with original jinja template, didn't encounter /n spam yet (but tested for only ~5hours at 100k context depth)

UPDATE: Nope fix didn't help, still getting /n spam sometimes

Also had issues with "/n" spam and model hanging when trying to tool call
I went in different direction - i've seen people fix the tool call issue through modifying parser code in llamacpp, can be seen here - https://github.com/ggml-org/llama.cpp/pull/26608
So i've sent my local AI on a mission to reuse code for tool call parser issues + attempt to fix the /n spam at the same time. Currently its working with original jinja template, didn't encounter /n spam yet (but tested for only ~5hours at 100k context depth)

UPDATE: Nope fix didn't help, still getting /n spam sometimes

i have burned 100$ in fable but still not able to fix the issues

I tried to reproduce the issues in this thread on my own machine (llama.cpp PR #26608, commit 3a0124f, Q4_K_M gguf, 128GB unified-memory box). There are actually 3 different problems mixed together here. That's why the fixes look like they don't work.

1. "Doesn't work with Claude Code"

Most likely cause: the two llama.cpp grammar bugs @gopi87 found (maxLength > 2000, and tools with empty parameters → failed to parse grammar). Claude Code's tool set triggers both on every request. These are llama.cpp core bugs (#25923 / #25927) and they are fixed now — I ran gopi87's two curl repros on the current PR branch, both pass. If you are on an old build or a fork, rebuild. Not a template problem.

2. Broken / hanging multi-argument tool calls

This was a real bug in PR #26608. Fixed in commit 0266ebca (Aug 7). I tested on a build after that commit, stock template + --jinja: 3-arg calls, optional args, multiline values, multi-turn tool use — all parse correctly.

@Kayook this is also why your test was confusing: the parser fix and the \n spam are different problems. The parser fix works. The spam has a different cause, see below.

3. The JSON template

I tested it. The model was not trained to output JSON arguments. Without grammar constraints it ignores the instruction and outputs <arg_key>/<arg_value> tags every time (6 out of 6 in my test). The JSON template only works because llama.cpp's grammar forces the format. The stock template already works on current builds, so I would keep the stock one.

There is one real bug in the stock template though: {% set _args = tc.arguments %} should be {%- set ... %}. It leaks a newline + 16 spaces after the function name, and the parser currently depends on that newline. One character fix.

4. The \n spam after 150k

I can reproduce the degradation, on a different stack than yours (PR #26608 instead of the prometheusAIR fork, Q4_K_M instead of Q8_0): generation falls into an exact repetition loop starting around 152–154k tokens (temp 0.6). In chat traffic this shows up as \n spam, since \n is the most common token there. Same test at 76k depth, same generation length: completely clean. So it's caused by context depth, not by sampling and not by the template. This matches gopi87's "works up to 150k" almost exactly. I could not reproduce spam at ~100k — my runs at 76k/117k/120k/130k were all clean.

Why people get different results: it depends on the gguf. AtomicChat and bloomer010 ggufs have context_length=131072, and llama-server caps the slot at that value — those users can never reach 150k at all. The prometheusAIR gguf has context_length=262144, so those users run straight into the bad zone. Also note Claude Code's token counter is not the same as the server-side position, which hides all this.

What works today: PR #26608 at or after 0266ebca + bloomer010 gguf + stock template + --jinja + context ≤ 131072. Don't override context_length to 262144. (AtomicChat ggufs currently don't load on the PR branch at all — old tensor names ssm_f/ssm_g, and block_count=42 with nextn_predict_layers=1 points to an MTP layer that is not in the file.)

I'll keep digging into the \n spam after 150k and post here when I find something.

Thanks @gopi87 — the grammar bug analysis was correct.

thanks @nehcoahz the model is really good on agent task and code generation and its better then qwen 3.6 27b. i think its gonna pair with coming qwen 3.8 27b & since its an moe its easy to use it. i keep on digging into the "n/" too will share what i find it .

i thnk i fixed the issues of "/n" repeation did tested above 185k its going fine i have attaching the found not sure if this is a fix or not

https://huggingface.co/gopi87/Lingflashfixclaudecode/blob/main/fix_documentation.pdf

echo 0 | sudo tee /proc/sys/kernel/numa_balancing
CUDA_VISIBLE_DEVICES=2,3,0,1
numactl --interleave=all
~/llama.cpp-bailing/build/bin/llama-server
--model /mnt/nvme/Ling-3.0-flash-Q8_0-00001-of-00004.gguf
--chat-template-file /mnt/nvme/bailing-tool-fix-v2.jinja
--tensor-split 1.2,1.8,0.45,0.35
--n-cpu-moe 42
-c 262144
--batch-size 8000
--ubatch-size 8000
--numa distribute
--no-mmap
--parallel 1
--threads 42
--threads-batch 42
-ngl 100
--host 127.0.0.1
--port 8082
--jinja 2>&1 | tee ~/llama-debug2.log

i used this

gopi@gopi-Super-Server:~$ echo 0 | sudo tee /proc/sys/kernel/numa_balancing
CUDA_VISIBLE_DEVICES=2,3,0,1
numactl --interleave=all
~/llama.cpp-bailing/build/bin/llama-server
--model /mnt/nvme/Ling-3.0-flash-Q8_0-00001-of-00004.gguf
--chat-template-file /mnt/nvme/bailing-tool-fix-v2.jinja
--reasoning-preserve
--tensor-split 2.2,2,0.5,0.35
--numa distribute
--no-mmap
-ot "blk.(41).ffn_(gate|down|up)exps.weight=CUDA2"
-ot "blk.(40).ffn(gate|down|up)exps.weight=CUDA1"
--n-cpu-moe 42
-c 262144
--batch-size 8500
--ubatch-size 8500
--threads 42
--threads-batch 42
-ngl 100
--host 127.0.0.1
--port 8082
--jinja
[sudo: authenticate] Password:
0
0.00.732.103 W DEPRECATED: --mmap and --no-mmap are deprecated. use --load-mode mmap instead
0.00.755.313 W DEPRECATED: argument '-ot' specified multiple times, use comma-separated values instead (only last value will be used)
0.00.802.052 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the -lv N CLI arg)
0.01.761.907 W srv llama_server: -----------------
0.01.761.918 W srv llama_server: CORS is set to allow all origins ('*') and no API key is set
0.01.761.919 W srv llama_server: this can be a security risk (cross-origin attacks)
0.01.761.919 W srv llama_server: more info: https://github.com/ggml-org/llama.cpp/pull/25655
0.01.761.920 W srv llama_server: -----------------
0.01.763.457 I srv load_model: loading model '/mnt/nvme/Ling-3.0-flash-Q8_0-00001-of-00004.gguf'
0.02.569.465 W common_fit_params: failed to fit params to free device memory: n_gpu_layers already set by user to 100, abort
0.02.898.428 W load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
0.03.182.029 W model has unused tensor blk.42.attn_norm.weight (size = 10240 bytes) -- ignoring
0.03.182.038 W model has unused tensor blk.42.attn_q.weight (size = 16711680 bytes) -- ignoring
0.03.182.043 W model has unused tensor blk.42.attn_kv_a_norm.weight (size = 2048 bytes) -- ignoring
0.03.182.048 W model has unused tensor blk.42.attn_kv_a_mqa.weight (size = 1566720 bytes) -- ignoring
0.03.182.057 W model has unused tensor blk.42.attn_k_b.weight (size = 2228224 bytes) -- ignoring
0.03.182.062 W model has unused tensor blk.42.attn_v_b.weight (size = 2228224 bytes) -- ignoring
0.03.182.066 W model has unused tensor blk.42.attn_gate.weight (size = 87040 bytes) -- ignoring
0.03.182.071 W model has unused tensor blk.42.attn_output.weight (size = 11141120 bytes) -- ignoring
0.03.182.077 W model has unused tensor blk.42.ffn_norm.weight (size = 10240 bytes) -- ignoring
0.03.182.082 W model has unused tensor blk.42.ffn_gate_inp.weight (size = 5242880 bytes) -- ignoring
0.03.182.086 W model has unused tensor blk.42.ffn_gate_exps.weight (size = 1069547520 bytes) -- ignoring
0.03.182.091 W model has unused tensor blk.42.ffn_down_exps.weight (size = 1069547520 bytes) -- ignoring
0.03.182.097 W model has unused tensor blk.42.ffn_up_exps.weight (size = 1069547520 bytes) -- ignoring
0.03.182.102 W model has unused tensor blk.42.ffn_gate_shexp.weight (size = 2088960 bytes) -- ignoring
0.03.182.107 W model has unused tensor blk.42.ffn_down_shexp.weight (size = 2088960 bytes) -- ignoring
0.03.182.112 W model has unused tensor blk.42.ffn_up_shexp.weight (size = 2088960 bytes) -- ignoring
0.03.182.117 W model has unused tensor blk.42.exp_probs_b.bias (size = 2048 bytes) -- ignoring
0.03.182.123 W model has unused tensor blk.42.nextn.eh_proj.weight (size = 13926400 bytes) -- ignoring
0.03.182.128 W model has unused tensor blk.42.nextn.enorm.weight (size = 10240 bytes) -- ignoring
0.03.182.133 W model has unused tensor blk.42.nextn.hnorm.weight (size = 10240 bytes) -- ignoring
0.03.182.138 W model has unused tensor blk.42.nextn.shared_head_norm.weight (size = 10240 bytes) -- ignoring
7.55.362.336 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 262144, kv_unified = 'true'
7.55.388.629 I srv llama_server: model loaded
7.55.388.639 I srv llama_server: listening on http://127.0.0.1:8082
8.03.685.152 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = -1
8.03.694.315 I slot launch_slot: id 3 | task 0 | processing task, is_child = 0
8.23.159.398 I slot print_timing: id 3 | task 0 | prompt processing, n_tokens = 8500, progress = 0.26, t = 19.46 s / 436.70 tokens per second
8.43.454.478 I slot print_timing: id 3 | task 0 | prompt processing, n_tokens = 17000, progress = 0.51, t = 39.76 s / 427.57 tokens per second
9.03.809.004 I slot print_timing: id 3 | task 0 | prompt processing, n_tokens = 24574, progress = 0.74, t = 60.11 s / 408.79 tokens per second
9.23.778.884 I slot print_timing: id 3 | task 0 | prompt processing, n_tokens = 30973, progress = 0.94, t = 80.08 s / 386.76 tokens per second
9.37.045.296 I slot print_timing: id 3 | task 0 | prompt processing, n_tokens = 33070, progress = 1.00, t = 93.35 s / 354.26 tokens per second
9.43.038.057 I slot print_timing: id 3 | task 0 | n_decoded = 100, tg = 17.32 t/s, tg_3s = 17.32 t/s
9.46.075.600 I slot print_timing: id 3 | task 0 | n_decoded = 154, tg = 17.48 t/s, tg_3s = 17.78 t/s
9.49.101.172 I slot print_timing: id 3 | task 0 | n_decoded = 208, tg = 17.57 t/s, tg_3s = 17.85 t/s
9.51.258.162 I slot print_timing: id 3 | task 0 | prompt eval time = 93570.28 ms / 33074 tokens ( 2.83 ms per token, 353.47 tokens per second)
9.51.258.166 I slot print_timing: id 3 | task 0 | eval time = 13992.75 ms / 246 tokens ( 56.88 ms per token, 17.58 tokens per second)
9.51.258.168 I slot print_timing: id 3 | task 0 | total time = 107563.04 ms / 33320 tokens
9.51.258.173 I slot print_timing: id 3 | task 0 | graphs reused = 244
9.51.260.389 I slot release: id 3 | task 0 | stop processing: n_tokens = 33319, truncated = 0
9.51.458.551 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = -1
9.51.460.927 I slot launch_slot_: id 2 | task 252 | processing task, is_child = 0
9.52.067.972 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = -1
9.52.178.592 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0
10.12.916.973 I slot print_timing: id 1 | task 253 | prompt processing, n_tokens = 575, progress = 1.00, t = 20.74 s / 27.73 tokens per second
10.13.001.123 I slot print_timing: id 2 | task 252 | prompt processing, n_tokens = 991, progress = 0.10, t = 20.72 s / 47.82 tokens per second
10.36.003.373 I slot print_timing: id 2 | task 252 | prompt processing, n_tokens = 8015, progress = 0.84, t = 43.72 s / 183.31 tokens per second
10.48.433.013 I slot print_timing: id 2 | task 252 | prompt processing, n_tokens = 9487, progress = 1.00, t = 56.15 s / 168.95 tokens per second
10.57.433.198 I slot print_timing: id 1 | task 253 | n_decoded = 100, tg = 4.67 t/s, tg_3s = 4.67 t/s
10.57.636.977 I slot print_timing: id 2 | task 252 | n_decoded = 100, tg = 11.20 t/s, tg_3s = 11.20 t/s
10.58.090.002 I slot print_timing: id 1 | task 253 | prompt eval time = 43823.99 ms / 579 tokens ( 75.69 ms per token, 13.21 tokens per second)
10.58.090.007 I slot print_timing: id 1 | task 253 | eval time = 22086.67 ms / 107 tokens ( 206.42 ms per token, 4.84 tokens per second)
10.58.090.009 I slot print_timing: id 1 | task 253 | total time = 65910.66 ms / 686 tokens
10.58.090.010 I slot print_timing: id 1 | task 253 | graphs reused = 346
10.58.092.206 I slot release: id 1 | task 253 | stop processing: n_tokens = 33755, truncated = 0
10.58.688.074 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.998
10.58.696.199 I slot launch_slot_: id 1 | task 371 | processing task, is_child = 0
11.14.877.639 I slot print_timing: id 2 | task 252 | n_decoded = 115, tg = 4.39 t/s, tg_3s = 0.87 t/s
11.14.877.713 I slot print_timing: id 1 | task 371 | prompt processing, n_tokens = 2691, progress = 1.00, t = 16.18 s / 166.31 tokens per second
11.17.944.081 I slot print_timing: id 2 | task 252 | n_decoded = 147, tg = 5.03 t/s, tg_3s = 10.44 t/s
11.21.024.657 I slot print_timing: id 2 | task 252 | n_decoded = 181, tg = 5.60 t/s, tg_3s = 11.04 t/s
11.23.019.836 I slot print_timing: id 1 | task 371 | prompt eval time = 16467.88 ms / 2695 tokens ( 6.11 ms per token, 163.65 tokens per second)
11.23.019.840 I slot print_timing: id 1 | task 371 | eval time = 7855.12 ms / 89 tokens ( 88.26 ms per token, 11.33 tokens per second)
11.23.019.842 I slot print_timing: id 1 | task 371 | total time = 24323.00 ms / 2784 tokens
11.23.019.844 I slot print_timing: id 1 | task 371 | graphs reused = 440
11.23.022.269 I slot release: id 1 | task 371 | stop processing: n_tokens = 36428, truncated = 0
11.24.034.410 I slot print_timing: id 2 | task 252 | n_decoded = 220, tg = 6.23 t/s, tg_3s = 12.96 t/s
11.25.761.077 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.999
11.25.769.888 I slot launch_slot_: id 1 | task 506 | processing task, is_child = 0
11.45.511.546 I slot print_timing: id 2 | task 252 | n_decoded = 249, tg = 4.38 t/s, tg_3s = 1.35 t/s
11.45.511.584 I slot print_timing: id 1 | task 506 | prompt processing, n_tokens = 4781, progress = 1.00, t = 19.74 s / 242.19 tokens per second
11.48.539.938 I slot print_timing: id 2 | task 252 | n_decoded = 280, tg = 4.68 t/s, tg_3s = 10.24 t/s
11.51.579.102 I slot print_timing: id 2 | task 252 | n_decoded = 315, tg = 5.01 t/s, tg_3s = 11.52 t/s
11.54.501.806 I slot print_timing: id 1 | task 506 | n_decoded = 100, tg = 11.48 t/s, tg_3s = 11.48 t/s
11.54.589.526 I slot print_timing: id 2 | task 252 | n_decoded = 350, tg = 5.31 t/s, tg_3s = 11.63 t/s
11.57.562.102 I slot print_timing: id 1 | task 506 | n_decoded = 136, tg = 11.55 t/s, tg_3s = 11.76 t/s
11.57.648.194 I slot print_timing: id 2 | task 252 | n_decoded = 386, tg = 5.60 t/s, tg_3s = 11.77 t/s
11.59.070.819 I slot print_timing: id 2 | task 252 | prompt eval time = 56426.92 ms / 9491 tokens ( 5.95 ms per token, 168.20 tokens per second)
11.59.070.823 I slot print_timing: id 2 | task 252 | eval time = 70364.52 ms / 402 tokens ( 175.04 ms per token, 5.71 tokens per second)
11.59.070.824 I slot print_timing: id 2 | task 252 | total time = 126791.45 ms / 9893 tokens
11.59.070.826 I slot print_timing: id 2 | task 252 | graphs reused = 633
11.59.071.679 I slot release: id 2 | task 252 | stop processing: n_tokens = 9892, truncated = 0
12.00.570.444 I slot print_timing: id 1 | task 506 | n_decoded = 177, tg = 11.98 t/s, tg_3s = 13.63 t/s
12.03.623.140 I slot print_timing: id 1 | task 506 | n_decoded = 227, tg = 12.73 t/s, tg_3s = 16.38 t/s
12.03.827.591 I slot print_timing: id 1 | task 506 | prompt eval time = 20019.88 ms / 4785 tokens ( 4.18 ms per token, 239.01 tokens per second)
12.03.827.595 I slot print_timing: id 1 | task 506 | eval time = 18037.10 ms / 230 tokens ( 78.42 ms per token, 12.75 tokens per second)
12.03.827.597 I slot print_timing: id 1 | task 506 | total time = 38056.98 ms / 5015 tokens
12.03.827.598 I slot print_timing: id 1 | task 506 | graphs reused = 708
12.03.830.150 I slot release: id 1 | task 506 | stop processing: n_tokens = 41350, truncated = 0
12.04.989.446 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.954 (> 0.100 thold), f_keep = 0.995
12.04.997.949 I slot launch_slot_: id 1 | task 738 | processing task, is_child = 0
12.19.588.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1
12.20.110.740 I slot launch_slot_: id 0 | task 740 | processing task, is_child = 0
12.20.208.018 I slot print_timing: id 1 | task 738 | prompt processing, n_tokens = 2038, progress = 1.00, t = 14.80 s / 137.66 tokens per second
12.45.756.383 I slot print_timing: id 0 | task 740 | prompt processing, n_tokens = 6601, progress = 1.00, t = 25.64 s / 257.40 tokens per second
12.54.709.126 I slot print_timing: id 1 | task 738 | n_decoded = 100, tg = 11.17 t/s, tg_3s = 11.17 t/s
12.54.794.744 I slot print_timing: id 0 | task 740 | n_decoded = 100, tg = 11.40 t/s, tg_3s = 11.40 t/s
12.57.727.450 I slot print_timing: id 1 | task 738 | n_decoded = 134, tg = 11.19 t/s, tg_3s = 11.26 t/s
12.57.816.875 I slot print_timing: id 0 | task 740 | n_decoded = 134, tg = 11.36 t/s, tg_3s = 11.25 t/s
13.00.811.483 I slot print_timing: id 1 | task 738 | n_decoded = 169, tg = 11.23 t/s, tg_3s = 11.35 t/s
13.00.892.358 I slot print_timing: id 0 | task 740 | n_decoded = 169, tg = 11.37 t/s, tg_3s = 11.38 t/s
13.03.894.127 I slot print_timing: id 0 | task 740 | n_decoded = 203, tg = 11.36 t/s, tg_3s = 11.33 t/s
13.03.897.782 I slot print_timing: id 1 | task 738 | n_decoded = 204, tg = 11.24 t/s, tg_3s = 11.34 t/s
13.05.222.684 I slot print_timing: id 1 | task 738 | prompt eval time = 40353.00 ms / 2042 tokens ( 19.76 ms per token, 50.60 tokens per second)
13.05.222.689 I slot print_timing: id 1 | task 738 | eval time = 19466.33 ms / 218 tokens ( 89.30 ms per token, 11.20 tokens per second)
13.05.222.690 I slot print_timing: id 1 | task 738 | total time = 59819.33 ms / 2260 tokens
13.05.222.708 I slot print_timing: id 1 | task 738 | graphs reused = 921
13.05.225.407 I slot release: id 1 | task 738 | stop processing: n_tokens = 43376, truncated = 0
13.06.252.122 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.776 (> 0.100 thold), f_keep = 0.997
13.06.260.238 I slot launch_slot_: id 1 | task 974 | processing task, is_child = 0
13.26.679.867 I slot print_timing: id 0 | task 740 | n_decoded = 234, tg = 5.76 t/s, tg_3s = 1.36 t/s
13.26.679.939 I slot print_timing: id 1 | task 974 | prompt processing, n_tokens = 4048, progress = 0.85, t = 20.42 s / 198.25 tokens per second
13.59.529.186 I slot print_timing: id 0 | task 740 | n_decoded = 235, tg = 3.20 t/s, tg_3s = 0.03 t/s
13.59.529.229 I slot print_timing: id 1 | task 974 | prompt processing, n_tokens = 12544, progress = 1.00, t = 53.27 s / 235.49 tokens per second
14.02.531.196 I slot print_timing: id 0 | task 740 | n_decoded = 266, tg = 3.48 t/s, tg_3s = 10.33 t/s
14.05.597.364 I slot print_timing: id 0 | task 740 | prompt eval time = 25914.11 ms / 6605 tokens ( 3.92 ms per token, 254.88 tokens per second)
14.05.597.369 I slot print_timing: id 0 | task 740 | eval time = 79571.77 ms / 301 tokens ( 264.36 ms per token, 3.78 tokens per second)
14.05.597.370 I slot print_timing: id 0 | task 740 | total time = 105485.88 ms / 6906 tokens
14.05.597.372 I slot print_timing: id 0 | task 740 | graphs reused = 1000
14.05.598.536 I slot release: id 0 | task 740 | stop processing: n_tokens = 16392, truncated = 0
14.07.763.020 I slot print_timing: id 1 | task 974 | n_decoded = 100, tg = 12.59 t/s, tg_3s = 12.59 t/s
14.10.805.074 I slot print_timing: id 1 | task 974 | n_decoded = 148, tg = 13.47 t/s, tg_3s = 15.78 t/s
14.11.244.928 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.806 (> 0.100 thold), f_keep = 0.988
14.11.246.997 I slot launch_slot_: id 0 | task 1133 | processing task, is_child = 0
14.32.189.059 I slot print_timing: id 1 | task 974 | n_decoded = 156, tg = 4.82 t/s, tg_3s = 0.37 t/s
14.32.189.090 I slot print_timing: id 0 | task 1133 | prompt processing, n_tokens = 3999, progress = 1.00, t = 20.94 s / 190.96 tokens per second
14.35.226.523 I slot print_timing: id 1 | task 974 | n_decoded = 187, tg = 5.28 t/s, tg_3s = 10.21 t/s
14.38.299.757 I slot print_timing: id 1 | task 974 | n_decoded = 221, tg = 5.74 t/s, tg_3s = 11.06 t/s
14.41.365.699 I slot print_timing: id 1 | task 974 | n_decoded = 255, tg = 6.14 t/s, tg_3s = 11.09 t/s
14.41.450.218 I slot print_timing: id 0 | task 1133 | n_decoded = 100, tg = 11.14 t/s, tg_3s = 11.14 t/s
14.43.323.622 I slot print_timing: id 1 | task 974 | prompt eval time = 53557.86 ms / 12548 tokens ( 4.27 ms per token, 234.29 tokens per second)
14.43.323.627 I slot print_timing: id 1 | task 974 | eval time = 43504.80 ms / 278 tokens ( 156.49 ms per token, 6.39 tokens per second)
14.43.323.628 I slot print_timing: id 1 | task 974 | total time = 97062.67 ms / 12826 tokens
14.43.323.629 I slot print_timing: id 1 | task 974 | graphs reused = 1206
14.43.327.669 I slot release: id 1 | task 974 | stop processing: n_tokens = 55980, truncated = 0
14.44.494.125 I slot print_timing: id 0 | task 1133 | n_decoded = 140, tg = 11.64 t/s, tg_3s = 13.14 t/s
14.45.177.112 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.562 (> 0.100 thold), f_keep = 0.997
14.45.185.201 I slot launch_slot_: id 1 | task 1286 | processing task, is_child = 0
15.20.192.357 I slot print_timing: id 0 | task 1133 | n_decoded = 152, tg = 3.19 t/s, tg_3s = 0.34 t/s
15.20.192.407 I slot print_timing: id 1 | task 1286 | prompt processing, n_tokens = 8499, progress = 0.65, t = 35.01 s / 242.78 tokens per second
15.56.999.496 I slot print_timing: id 0 | task 1133 | n_decoded = 153, tg = 1.81 t/s, tg_3s = 0.03 t/s
15.56.999.570 I slot print_timing: id 1 | task 1286 | prompt processing, n_tokens = 16998, progress = 0.73, t = 71.81 s / 236.70 tokens per second
16.35.152.537 I slot print_timing: id 0 | task 1133 | n_decoded = 154, tg = 1.26 t/s, tg_3s = 0.03 t/s
16.35.152.580 I slot print_timing: id 1 | task 1286 | prompt processing, n_tokens = 25497, progress = 0.82, t = 109.97 s / 231.86 tokens per second
17.14.974.935 I slot print_timing: id 0 | task 1133 | n_decoded = 155, tg = 0.95 t/s, tg_3s = 0.03 t/s
17.14.974.962 I slot print_timing: id 1 | task 1286 | prompt processing, n_tokens = 33996, progress = 0.90, t = 149.79 s / 226.96 tokens per second
17.26.028.572 I slot print_timing: id 0 | task 1133 | n_decoded = 156, tg = 0.90 t/s, tg_3s = 0.09 t/s
17.26.028.600 I slot print_timing: id 1 | task 1286 | prompt processing, n_tokens = 35080, progress = 0.91, t = 160.84 s / 218.10 tokens per second
18.07.638.360 I slot print_timing: id 0 | task 1133 | n_decoded = 157, tg = 0.73 t/s, tg_3s = 0.02 t/s
18.07.638.387 I slot print_timing: id 1 | task 1286 | prompt processing, n_tokens = 43576, progress = 1.00, t = 202.45 s / 215.24 tokens per second
18.10.753.954 I slot print_timing: id 0 | task 1133 | n_decoded = 186, tg = 0.85 t/s, tg_3s = 9.31 t/s
18.13.841.248 I slot print_timing: id 0 | task 1133 | n_decoded = 219, tg = 0.99 t/s, tg_3s = 10.69 t/s
18.16.854.276 I slot print_timing: id 0 | task 1133 | n_decoded = 251, tg = 1.12 t/s, tg_3s = 10.62 t/s
18.17.402.246 I slot print_timing: id 1 | task 1286 | n_decoded = 100, tg = 10.58 t/s, tg_3s = 10.58 t/s
18.19.881.680 I slot print_timing: id 0 | task 1133 | n_decoded = 283, tg = 1.24 t/s, tg_3s = 10.57 t/s
18.20.423.154 I slot print_timing: id 1 | task 1286 | n_decoded = 132, tg = 10.58 t/s, tg_3s = 10.59 t/s
18.21.948.789 I slot print_timing: id 0 | task 1133 | prompt eval time = 21222.03 ms / 4003 tokens ( 5.30 ms per token, 188.62 tokens per second)
18.21.948.811 I slot print_timing: id 0 | task 1133 | eval time = 229478.96 ms / 305 tokens ( 752.39 ms per token, 1.33 tokens per second)
18.21.948.813 I slot print_timing: id 0 | task 1133 | total time = 250700.99 ms / 4308 tokens
18.21.948.814 I slot print_timing: id 0 | task 1133 | graphs reused = 1378
18.21.950.087 I slot release: id 0 | task 1133 | stop processing: n_tokens = 20395, truncated = 0
18.23.355.735 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.765 (> 0.100 thold), f_keep = 0.989
18.23.357.880 I slot launch_slot_: id 0 | task 1462 | processing task, is_child = 0
18.57.929.914 I slot print_timing: id 1 | task 1286 | n_decoded = 170, tg = 3.40 t/s, tg_3s = 1.01 t/s
18.57.929.976 I slot print_timing: id 0 | task 1462 | prompt processing, n_tokens = 6288, progress = 1.00, t = 34.57 s / 181.89 tokens per second
19.00.963.709 I slot print_timing: id 1 | task 1286 | n_decoded = 200, tg = 3.77 t/s, tg_3s = 9.89 t/s
19.03.991.176 I slot print_timing: id 1 | task 1286 | n_decoded = 233, tg = 4.16 t/s, tg_3s = 10.90 t/s
19.07.056.248 I slot print_timing: id 1 | task 1286 | n_decoded = 265, tg = 4.48 t/s, tg_3s = 10.44 t/s
19.07.509.607 I slot print_timing: id 0 | task 1462 | n_decoded = 100, tg = 10.78 t/s, tg_3s = 10.78 t/s
19.10.098.178 I slot print_timing: id 1 | task 1286 | n_decoded = 297, tg = 4.78 t/s, tg_3s = 10.52 t/s
19.10.555.827 I slot print_timing: id 0 | task 1462 | n_decoded = 132, tg = 10.71 t/s, tg_3s = 10.50 t/s
19.13.159.613 I slot print_timing: id 1 | task 1286 | n_decoded = 330, tg = 5.06 t/s, tg_3s = 10.78 t/s
19.13.620.675 I slot print_timing: id 0 | task 1462 | n_decoded = 165, tg = 10.72 t/s, tg_3s = 10.77 t/s
19.16.263.417 I slot print_timing: id 1 | task 1286 | n_decoded = 363, tg = 5.31 t/s, tg_3s = 10.63 t/s
19.16.632.363 I slot print_timing: id 0 | task 1462 | n_decoded = 197, tg = 10.71 t/s, tg_3s = 10.63 t/s
19.19.320.446 I slot print_timing: id 1 | task 1286 | n_decoded = 396, tg = 5.55 t/s, tg_3s = 10.79 t/s
19.19.685.478 I slot print_timing: id 0 | task 1462 | n_decoded = 230, tg = 10.72 t/s, tg_3s = 10.81 t/s
19.19.985.576 I slot print_timing: id 1 | task 1286 | prompt eval time = 202766.50 ms / 43580 tokens ( 4.65 ms per token, 214.93 tokens per second)
19.19.985.581 I slot print_timing: id 1 | task 1286 | eval time = 72033.10 ms / 403 tokens ( 178.74 ms per token, 5.59 tokens per second)
19.19.985.582 I slot print_timing: id 1 | task 1286 | total time = 274799.59 ms / 43983 tokens
19.19.985.584 I slot print_timing: id 1 | task 1286 | graphs reused = 1627
19.19.991.464 I slot release: id 1 | task 1286 | stop processing: n_tokens = 99681, truncated = 0
19.20.295.095 I slot get_availabl: id 3 | task -1 | selected slot by LRU, t_last = 18490364483
19.20.299.639 I slot launch_slot_: id 3 | task 1701 | processing task, is_child = 0
19.21.709.168 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 18618175772
19.26.725.458 I slot launch_slot_: id 2 | task 1702 | processing task, is_child = 0
20.10.570.407 I slot print_timing: id 0 | task 1462 | n_decoded = 238, tg = 3.29 t/s, tg_3s = 0.16 t/s
20.10.570.454 I slot print_timing: id 2 | task 1702 | prompt processing, n_tokens = 777, progress = 1.00, t = 43.84 s / 17.72 tokens per second
20.10.667.976 I slot print_timing: id 3 | task 1701 | prompt processing, n_tokens = 5566, progress = 0.40, t = 43.85 s / 126.93 tokens per second
20.47.381.119 I slot print_timing: id 0 | task 1462 | n_decoded = 239, tg = 2.19 t/s, tg_3s = 0.03 t/s
20.47.384.502 I slot print_timing: id 3 | task 1701 | prompt processing, n_tokens = 12297, progress = 0.87, t = 80.57 s / 152.63 tokens per second
21.04.687.803 I slot print_timing: id 0 | task 1462 | n_decoded = 240, tg = 1.90 t/s, tg_3s = 0.06 t/s
21.04.690.860 I slot print_timing: id 3 | task 1701 | prompt processing, n_tokens = 14062, progress = 1.00, t = 97.87 s / 143.67 tokens per second
21.07.750.844 I slot print_timing: id 0 | task 1462 | n_decoded = 263, tg = 2.03 t/s, tg_3s = 7.51 t/s
21.10.761.457 I slot print_timing: id 0 | task 1462 | n_decoded = 288, tg = 2.17 t/s, tg_3s = 8.30 t/s
21.13.809.696 I slot print_timing: id 0 | task 1462 | n_decoded = 312, tg = 2.30 t/s, tg_3s = 7.87 t/s
21.16.872.585 I slot print_timing: id 0 | task 1462 | n_decoded = 337, tg = 2.43 t/s, tg_3s = 8.16 t/s
21.16.996.784 I slot print_timing: id 2 | task 1702 | n_decoded = 100, tg = 3.38 t/s, tg_3s = 3.38 t/s
21.17.233.541 I slot print_timing: id 3 | task 1701 | n_decoded = 100, tg = 8.18 t/s, tg_3s = 8.18 t/s
21.18.000.850 I slot print_timing: id 3 | task 1701 | prompt eval time = 98199.02 ms / 14066 tokens ( 6.98 ms per token, 143.24 tokens per second)
21.18.000.855 I slot print_timing: id 3 | task 1701 | eval time = 12985.01 ms / 106 tokens ( 122.50 ms per token, 8.16 tokens per second)
21.18.000.856 I slot print_timing: id 3 | task 1701 | total time = 111184.03 ms / 14172 tokens
21.18.000.858 I slot print_timing: id 3 | task 1701 | graphs reused = 1732
21.18.001.934 I slot release: id 3 | task 1701 | stop processing: n_tokens = 14171, truncated = 0
21.18.577.294 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.675 (> 0.100 thold), f_keep = 0.996
21.18.580.713 I slot launch_slot_: id 3 | task 1817 | processing task, is_child = 0
21.58.490.564 I slot print_timing: id 0 | task 1462 | n_decoded = 352, tg = 1.95 t/s, tg_3s = 0.36 t/s
21.58.493.861 I slot print_timing: id 2 | task 1702 | n_decoded = 114, tg = 1.60 t/s, tg_3s = 0.34 t/s
21.58.493.893 I slot print_timing: id 3 | task 1817 | prompt processing, n_tokens = 6848, progress = 1.00, t = 39.91 s / 171.58 tokens per second
22.01.514.535 I slot print_timing: id 0 | task 1462 | n_decoded = 375, tg = 2.05 t/s, tg_3s = 7.61 t/s
22.01.517.873 I slot print_timing: id 2 | task 1702 | n_decoded = 137, tg = 1.85 t/s, tg_3s = 7.61 t/s
22.02.259.731 I slot print_timing: id 0 | task 1462 | prompt eval time = 34872.00 ms / 6292 tokens ( 5.54 ms per token, 180.43 tokens per second)
22.02.259.736 I slot print_timing: id 0 | task 1462 | eval time = 184028.88 ms / 381 tokens ( 483.02 ms per token, 2.07 tokens per second)
22.02.259.737 I slot print_timing: id 0 | task 1462 | total time = 218900.88 ms / 6673 tokens
22.02.259.738 I slot print_timing: id 0 | task 1462 | graphs reused = 1763
22.02.261.306 I slot release: id 0 | task 1462 | stop processing: n_tokens = 26759, truncated = 0
22.03.835.795 I slot print_timing: id 2 | task 1702 | prompt eval time = 80658.25 ms / 781 tokens ( 103.28 ms per token, 9.68 tokens per second)
22.03.835.800 I slot print_timing: id 2 | task 1702 | eval time = 76451.30 ms / 159 tokens ( 480.83 ms per token, 2.08 tokens per second)
22.03.835.802 I slot print_timing: id 2 | task 1702 | total time = 157109.55 ms / 940 tokens
22.03.835.803 I slot print_timing: id 2 | task 1702 | graphs reused = 1778
22.03.840.657 I slot release: id 2 | task 1702 | stop processing: n_tokens = 100214, truncated = 0
22.05.421.905 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.737 (> 0.100 thold), f_keep = 0.999
22.05.429.996 I slot launch_slot_: id 2 | task 1886 | processing task, is_child = 0
22.49.637.722 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 19059095557
22.51.066.260 I slot launch_slot_: id 1 | task 1888 | processing task, is_child = 0
23.40.800.223 I slot print_timing: id 1 | task 1888 | prompt processing, n_tokens = 8499, progress = 0.55, t = 49.73 s / 170.89 tokens per second
24.31.864.131 I slot print_timing: id 1 | task 1888 | prompt processing, n_tokens = 16998, progress = 0.68, t = 100.80 s / 168.64 tokens per second
25.24.628.626 I slot print_timing: id 1 | task 1888 | prompt processing, n_tokens = 25497, progress = 0.82, t = 153.56 s / 166.04 tokens per second
25.24.629.259 I slot print_timing: id 2 | task 1886 | prompt processing, n_tokens = 8499, progress = 0.80, t = 198.50 s / 42.82 tokens per second
26.28.934.709 I slot print_timing: id 1 | task 1888 | prompt processing, n_tokens = 28523, progress = 0.87, t = 217.87 s / 130.92 tokens per second
26.29.019.102 I slot print_timing: id 2 | task 1886 | prompt processing, n_tokens = 13972, progress = 0.84, t = 262.89 s / 53.15 tokens per second
27.25.764.698 I slot print_timing: id 1 | task 1888 | prompt processing, n_tokens = 37019, progress = 1.00, t = 274.70 s / 134.76 tokens per second
27.25.857.609 I slot print_timing: id 2 | task 1886 | prompt processing, n_tokens = 13975, progress = 0.84, t = 319.73 s / 43.71 tokens per second
28.24.043.977 I slot print_timing: id 2 | task 1886 | prompt processing, n_tokens = 22470, progress = 0.90, t = 377.91 s / 59.46 tokens per second
29.01.340.611 I slot print_timing: id 2 | task 1886 | prompt processing, n_tokens = 27265, progress = 0.94, t = 415.21 s / 65.67 tokens per second
30.02.179.392 I slot print_timing: id 2 | task 1886 | prompt processing, n_tokens = 35761, progress = 1.00, t = 476.05 s / 75.12 tokens per second
30.05.649.944 I slot print_timing: id 3 | task 1817 | n_decoded = 100, tg = 0.21 t/s, tg_3s = 0.21 t/s
30.08.769.946 I slot print_timing: id 3 | task 1817 | n_decoded = 123, tg = 0.25 t/s, tg_3s = 7.37 t/s
30.11.826.111 I slot print_timing: id 3 | task 1817 | n_decoded = 146, tg = 0.30 t/s, tg_3s = 7.53 t/s
30.14.947.172 I slot print_timing: id 3 | task 1817 | n_decoded = 169, tg = 0.34 t/s, tg_3s = 7.37 t/s
30.15.478.626 I slot print_timing: id 1 | task 1888 | n_decoded = 100, tg = 0.90 t/s, tg_3s = 0.90 t/s
30.15.617.809 I slot print_timing: id 3 | task 1817 | prompt eval time = 40234.36 ms / 6852 tokens ( 5.87 ms per token, 170.30 tokens per second)
30.15.617.814 I slot print_timing: id 3 | task 1817 | eval time = 496801.96 ms / 174 tokens ( 2855.18 ms per token, 0.35 tokens per second)
30.15.617.815 I slot print_timing: id 3 | task 1817 | total time = 537036.31 ms / 7026 tokens
30.15.617.816 I slot print_timing: id 3 | task 1817 | graphs reused = 1894
30.15.619.268 I slot release: id 3 | task 1817 | stop processing: n_tokens = 21087, truncated = 0
30.15.868.794 I slot print_timing: id 2 | task 1886 | n_decoded = 100, tg = 7.51 t/s, tg_3s = 7.51 t/s
30.18.133.298 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.770 (> 0.100 thold), f_keep = 0.995
30.18.137.002 I slot launch_slot_: id 3 | task 2019 | processing task, is_child = 0
31.07.594.149 I slot print_timing: id 1 | task 1888 | n_decoded = 126, tg = 0.77 t/s, tg_3s = 0.50 t/s
31.07.597.237 I slot print_timing: id 2 | task 1886 | n_decoded = 123, tg = 1.89 t/s, tg_3s = 0.44 t/s
31.07.597.265 I slot print_timing: id 3 | task 2019 | prompt processing, n_tokens = 6332, progress = 1.00, t = 49.46 s / 128.03 tokens per second
31.10.692.042 I slot print_timing: id 1 | task 1888 | n_decoded = 147, tg = 0.88 t/s, tg_3s = 6.78 t/s
31.10.695.072 I slot print_timing: id 2 | task 1886 | n_decoded = 144, tg = 2.11 t/s, tg_3s = 6.78 t/s
31.13.718.549 I slot print_timing: id 1 | task 1888 | n_decoded = 169, tg = 1.00 t/s, tg_3s = 7.27 t/s
31.13.722.644 I slot print_timing: id 2 | task 1886 | n_decoded = 166, tg = 2.33 t/s, tg_3s = 7.27 t/s
31.16.840.987 I slot print_timing: id 1 | task 1888 | n_decoded = 192, tg = 1.11 t/s, tg_3s = 7.37 t/s
31.16.844.137 I slot print_timing: id 2 | task 1886 | n_decoded = 189, tg = 2.54 t/s, tg_3s = 7.37 t/s
31.19.946.771 I slot print_timing: id 1 | task 1888 | n_decoded = 215, tg = 1.22 t/s, tg_3s = 7.41 t/s
31.19.949.948 I slot print_timing: id 2 | task 1886 | n_decoded = 212, tg = 2.74 t/s, tg_3s = 7.41 t/s
31.21.445.772 I slot print_timing: id 3 | task 2019 | n_decoded = 100, tg = 7.40 t/s, tg_3s = 7.40 t/s
31.23.030.549 I slot print_timing: id 1 | task 1888 | n_decoded = 238, tg = 1.33 t/s, tg_3s = 7.46 t/s
31.23.033.770 I slot print_timing: id 2 | task 1886 | n_decoded = 235, tg = 2.92 t/s, tg_3s = 7.46 t/s
31.24.513.576 I slot print_timing: id 3 | task 2019 | n_decoded = 123, tg = 7.42 t/s, tg_3s = 7.50 t/s
31.26.108.802 I slot print_timing: id 1 | task 1888 | n_decoded = 261, tg = 1.43 t/s, tg_3s = 7.47 t/s
31.26.112.339 I slot print_timing: id 2 | task 1886 | n_decoded = 258, tg = 3.09 t/s, tg_3s = 7.47 t/s
31.27.578.420 I slot print_timing: id 3 | task 2019 | n_decoded = 146, tg = 7.43 t/s, tg_3s = 7.50 t/s
31.29.167.936 I slot print_timing: id 1 | task 1888 | n_decoded = 284, tg = 1.53 t/s, tg_3s = 7.52 t/s
31.29.171.304 I slot print_timing: id 2 | task 1886 | n_decoded = 281, tg = 3.24 t/s, tg_3s = 7.52 t/s
31.30.609.882 I slot print_timing: id 3 | task 2019 | n_decoded = 169, tg = 7.45 t/s, tg_3s = 7.59 t/s
31.32.218.856 I slot print_timing: id 1 | task 1888 | n_decoded = 306, tg = 1.63 t/s, tg_3s = 7.21 t/s
31.32.222.111 I slot print_timing: id 2 | task 1886 | n_decoded = 303, tg = 3.38 t/s, tg_3s = 7.21 t/s
31.33.668.696 I slot print_timing: id 3 | task 2019 | n_decoded = 191, tg = 7.42 t/s, tg_3s = 7.19 t/s
31.35.334.143 I slot print_timing: id 1 | task 1888 | n_decoded = 327, tg = 1.71 t/s, tg_3s = 6.74 t/s
31.35.337.263 I slot print_timing: id 2 | task 1886 | n_decoded = 324, tg = 3.49 t/s, tg_3s = 6.74 t/s
31.36.757.262 I slot print_timing: id 3 | task 2019 | n_decoded = 210, tg = 7.29 t/s, tg_3s = 6.15 t/s
31.38.495.386 I slot print_timing: id 1 | task 1888 | n_decoded = 347, tg = 1.78 t/s, tg_3s = 6.33 t/s
31.38.498.508 I slot print_timing: id 2 | task 1886 | n_decoded = 344, tg = 3.59 t/s, tg_3s = 6.33 t/s
31.39.889.684 I slot print_timing: id 3 | task 2019 | n_decoded = 230, tg = 7.20 t/s, tg_3s = 6.38 t/s
31.41.210.751 I slot print_timing: id 1 | task 1888 | prompt eval time = 332973.47 ms / 37023 tokens ( 8.99 ms per token, 111.19 tokens per second)
31.41.210.773 I slot print_timing: id 1 | task 1888 | eval time = 197170.08 ms / 365 tokens ( 540.19 ms per token, 1.85 tokens per second)
31.41.210.774 I slot print_timing: id 1 | task 1888 | total time = 530143.55 ms / 37388 tokens
31.41.210.775 I slot print_timing: id 1 | task 1888 | graphs reused = 2151
31.41.214.096 I slot release: id 1 | task 1888 | stop processing: n_tokens = 63762, truncated = 0
31.41.576.945 I slot print_timing: id 2 | task 1886 | n_decoded = 365, tg = 3.69 t/s, tg_3s = 6.82 t/s
31.42.928.898 I slot print_timing: id 3 | task 2019 | n_decoded = 255, tg = 7.29 t/s, tg_3s = 8.23 t/s
31.43.873.537 I slot print_timing: id 3 | task 2019 | prompt eval time = 49800.68 ms / 6336 tokens ( 7.86 ms per token, 127.23 tokens per second)
31.43.873.561 I slot print_timing: id 3 | task 2019 | eval time = 35934.46 ms / 264 tokens ( 136.12 ms per token, 7.35 tokens per second)
31.43.873.562 I slot print_timing: id 3 | task 2019 | total time = 85735.14 ms / 6600 tokens
31.43.873.564 I slot print_timing: id 3 | task 2019 | graphs reused = 2175
31.43.875.198 I slot release: id 3 | task 2019 | stop processing: n_tokens = 27509, truncated = 0
31.44.640.403 I slot print_timing: id 2 | task 1886 | n_decoded = 397, tg = 3.89 t/s, tg_3s = 10.45 t/s
31.44.640.469 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.503 (> 0.100 thold), f_keep = 0.992
31.44.643.671 I slot launch_slot_: id 3 | task 2295 | processing task, is_child = 0
31.45.729.498 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 19221365398
31.49.121.921 I slot launch_slot_: id 0 | task 2296 | processing task, is_child = 0
33.02.199.629 I slot print_timing: id 2 | task 1886 | n_decoded = 398, tg = 2.22 t/s, tg_3s = 0.01 t/s
33.02.199.696 I slot print_timing: id 0 | task 2296 | prompt processing, n_tokens = 6527, progress = 1.00, t = 73.08 s / 89.32 tokens per second
33.02.296.401 I slot print_timing: id 3 | task 2295 | prompt processing, n_tokens = 1972, progress = 0.54, t = 73.08 s / 26.98 tokens per second
34.07.852.878 I slot print_timing: id 2 | task 1886 | n_decoded = 399, tg = 1.63 t/s, tg_3s = 0.02 t/s
34.07.852.917 I slot print_timing: id 3 | task 2295 | prompt processing, n_tokens = 10467, progress = 0.70, t = 138.64 s / 75.50 tokens per second
35.11.885.471 I slot print_timing: id 2 | task 1886 | n_decoded = 400, tg = 1.29 t/s, tg_3s = 0.02 t/s
35.11.885.501 I slot print_timing: id 3 | task 2295 | prompt processing, n_tokens = 18503, progress = 0.84, t = 202.67 s / 91.30 tokens per second
36.20.515.419 I slot print_timing: id 2 | task 1886 | n_decoded = 401, tg = 1.06 t/s, tg_3s = 0.01 t/s
36.20.515.451 I slot print_timing: id 3 | task 2295 | prompt processing, n_tokens = 26999, progress = 1.00, t = 271.30 s / 99.52 tokens per second
36.23.577.797 I slot print_timing: id 2 | task 1886 | n_decoded = 422, tg = 1.11 t/s, tg_3s = 6.86 t/s
36.26.677.827 I slot print_timing: id 2 | task 1886 | n_decoded = 445, tg = 1.16 t/s, tg_3s = 7.42 t/s
36.29.684.691 I slot print_timing: id 2 | task 1886 | n_decoded = 467, tg = 1.21 t/s, tg_3s = 7.32 t/s
36.32.694.026 I slot print_timing: id 2 | task 1886 | prompt eval time = 476424.34 ms / 35765 tokens ( 13.32 ms per token, 75.07 tokens per second)
36.32.694.031 I slot print_timing: id 2 | task 1886 | eval time = 390137.20 ms / 488 tokens ( 799.46 ms per token, 1.25 tokens per second)
36.32.694.033 I slot print_timing: id 2 | task 1886 | total time = 866561.54 ms / 36253 tokens
36.32.694.035 I slot print_timing: id 2 | task 1886 | graphs reused = 2268
36.32.699.957 I slot release: id 2 | task 1886 | stop processing: n_tokens = 136304, truncated = 0
36.32.961.093 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 19800318190
36.32.964.827 I slot launch_slot_: id 1 | task 2390 | processing task, is_child = 0
36.34.833.523 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 20091804050
36.41.653.721 I slot launch_slot_: id 2 | task 2391 | processing task, is_child = 0
36.41.686.459 E init_batch: failed to prepare attention ubatches
36.41.686.471 W decode: failed to find a memory slot for batch of size 8164
36.41.686.473 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 0, n_batch = 4250, ret = 1
36.41.699.248 E init_batch: failed to prepare attention ubatches
36.41.699.255 W decode: failed to find a memory slot for batch of size 4250
36.41.699.258 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 0, n_batch = 2125, ret = 1
36.41.711.218 E init_batch: failed to prepare attention ubatches
36.41.711.223 W decode: failed to find a memory slot for batch of size 2125
36.41.711.224 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 0, n_batch = 1062, ret = 1
36.57.567.039 E init_batch: failed to prepare attention ubatches
36.57.567.048 W decode: failed to find a memory slot for batch of size 7102
36.57.567.068 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1062, n_batch = 4250, ret = 1
36.57.575.488 E init_batch: failed to prepare attention ubatches
36.57.575.492 W decode: failed to find a memory slot for batch of size 4250
36.57.575.493 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1062, n_batch = 2125, ret = 1
36.57.583.008 E init_batch: failed to prepare attention ubatches
36.57.583.012 W decode: failed to find a memory slot for batch of size 2125
36.57.583.013 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1062, n_batch = 1062, ret = 1
36.57.589.939 E init_batch: failed to prepare attention ubatches
36.57.589.943 W decode: failed to find a memory slot for batch of size 1062
36.57.589.944 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1062, n_batch = 531, ret = 1
37.08.220.745 E init_batch: failed to prepare attention ubatches
37.08.220.755 W decode: failed to find a memory slot for batch of size 6571
37.08.220.760 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1593, n_batch = 4250, ret = 1
37.08.229.073 E init_batch: failed to prepare attention ubatches
37.08.229.078 W decode: failed to find a memory slot for batch of size 4250
37.08.229.079 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1593, n_batch = 2125, ret = 1
37.08.236.309 E init_batch: failed to prepare attention ubatches
37.08.236.313 W decode: failed to find a memory slot for batch of size 2125
37.08.236.314 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1593, n_batch = 1062, ret = 1
37.08.243.204 E init_batch: failed to prepare attention ubatches
37.08.243.207 W decode: failed to find a memory slot for batch of size 1062
37.08.243.208 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1593, n_batch = 531, ret = 1
37.08.250.139 E init_batch: failed to prepare attention ubatches
37.08.250.143 W decode: failed to find a memory slot for batch of size 531
37.08.250.145 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1593, n_batch = 265, ret = 1
37.15.684.174 E init_batch: failed to prepare attention ubatches
37.15.684.193 W decode: failed to find a memory slot for batch of size 6306
37.15.684.199 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1858, n_batch = 4250, ret = 1
37.15.692.572 E init_batch: failed to prepare attention ubatches
37.15.692.577 W decode: failed to find a memory slot for batch of size 4250
37.15.692.579 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1858, n_batch = 2125, ret = 1
37.15.699.917 E init_batch: failed to prepare attention ubatches
37.15.699.922 W decode: failed to find a memory slot for batch of size 2125
37.15.699.923 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1858, n_batch = 1062, ret = 1
37.15.707.079 E init_batch: failed to prepare attention ubatches
37.15.707.082 W decode: failed to find a memory slot for batch of size 1062
37.15.707.084 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1858, n_batch = 531, ret = 1
37.15.713.566 E init_batch: failed to prepare attention ubatches
37.15.713.570 W decode: failed to find a memory slot for batch of size 531
37.15.713.571 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1858, n_batch = 265, ret = 1
37.15.720.415 E init_batch: failed to prepare attention ubatches
37.15.720.418 W decode: failed to find a memory slot for batch of size 265
37.15.720.419 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1858, n_batch = 132, ret = 1
37.15.727.280 E init_batch: failed to prepare attention ubatches
37.15.727.284 W decode: failed to find a memory slot for batch of size 132
37.15.727.285 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1858, n_batch = 66, ret = 1
37.19.514.492 E init_batch: failed to prepare attention ubatches
37.19.514.501 W decode: failed to find a memory slot for batch of size 6240
37.19.514.505 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1924, n_batch = 4250, ret = 1
37.19.522.692 E init_batch: failed to prepare attention ubatches
37.19.522.697 W decode: failed to find a memory slot for batch of size 4250
37.19.522.698 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1924, n_batch = 2125, ret = 1
37.19.529.794 E init_batch: failed to prepare attention ubatches
37.19.529.797 W decode: failed to find a memory slot for batch of size 2125
37.19.529.798 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1924, n_batch = 1062, ret = 1
37.19.536.780 E init_batch: failed to prepare attention ubatches
37.19.536.787 W decode: failed to find a memory slot for batch of size 1062
37.19.536.789 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1924, n_batch = 531, ret = 1
37.19.543.378 E init_batch: failed to prepare attention ubatches
37.19.543.381 W decode: failed to find a memory slot for batch of size 531
37.19.543.382 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1924, n_batch = 265, ret = 1
37.19.550.077 E init_batch: failed to prepare attention ubatches
37.19.550.082 W decode: failed to find a memory slot for batch of size 265
37.19.550.089 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1924, n_batch = 132, ret = 1
37.19.556.816 E init_batch: failed to prepare attention ubatches
37.19.556.819 W decode: failed to find a memory slot for batch of size 132
37.19.556.821 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1924, n_batch = 66, ret = 1
37.19.563.203 E init_batch: failed to prepare attention ubatches
37.19.563.207 W decode: failed to find a memory slot for batch of size 66
37.19.563.208 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1924, n_batch = 33, ret = 1
37.22.054.108 E init_batch: failed to prepare attention ubatches
37.22.054.117 W decode: failed to find a memory slot for batch of size 6207
37.22.054.120 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1957, n_batch = 4250, ret = 1
37.22.062.182 E init_batch: failed to prepare attention ubatches
37.22.062.187 W decode: failed to find a memory slot for batch of size 4250
37.22.062.188 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1957, n_batch = 2125, ret = 1
37.22.069.615 E init_batch: failed to prepare attention ubatches
37.22.069.619 W decode: failed to find a memory slot for batch of size 2125
37.22.069.620 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1957, n_batch = 1062, ret = 1
37.22.076.680 E init_batch: failed to prepare attention ubatches
37.22.076.684 W decode: failed to find a memory slot for batch of size 1062
37.22.076.685 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1957, n_batch = 531, ret = 1
37.22.083.492 E init_batch: failed to prepare attention ubatches
37.22.083.495 W decode: failed to find a memory slot for batch of size 531
37.22.083.496 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1957, n_batch = 265, ret = 1
37.22.090.027 E init_batch: failed to prepare attention ubatches
37.22.090.031 W decode: failed to find a memory slot for batch of size 265
37.22.090.032 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1957, n_batch = 132, ret = 1
37.22.096.619 E init_batch: failed to prepare attention ubatches
37.22.096.623 W decode: failed to find a memory slot for batch of size 132
37.22.096.624 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1957, n_batch = 66, ret = 1
37.22.103.406 E init_batch: failed to prepare attention ubatches
37.22.103.410 W decode: failed to find a memory slot for batch of size 66
37.22.103.411 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1957, n_batch = 33, ret = 1
37.22.109.904 E init_batch: failed to prepare attention ubatches
37.22.109.907 W decode: failed to find a memory slot for batch of size 33
37.22.109.913 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1957, n_batch = 16, ret = 1
37.22.451.889 E init_batch: failed to prepare attention ubatches
37.22.451.899 W decode: failed to find a memory slot for batch of size 6191
37.22.451.927 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 4250, ret = 1
37.22.460.295 E init_batch: failed to prepare attention ubatches
37.22.460.300 W decode: failed to find a memory slot for batch of size 4250
37.22.460.301 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 2125, ret = 1
37.22.467.484 E init_batch: failed to prepare attention ubatches
37.22.467.488 W decode: failed to find a memory slot for batch of size 2125
37.22.467.489 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 1062, ret = 1
37.22.474.535 E init_batch: failed to prepare attention ubatches
37.22.474.540 W decode: failed to find a memory slot for batch of size 1062
37.22.474.541 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 531, ret = 1
37.22.481.491 E init_batch: failed to prepare attention ubatches
37.22.481.496 W decode: failed to find a memory slot for batch of size 531
37.22.481.497 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 265, ret = 1
37.22.488.619 E init_batch: failed to prepare attention ubatches
37.22.488.625 W decode: failed to find a memory slot for batch of size 265
37.22.488.627 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 132, ret = 1
37.22.495.685 E init_batch: failed to prepare attention ubatches
37.22.495.690 W decode: failed to find a memory slot for batch of size 132
37.22.495.691 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 66, ret = 1
37.22.502.807 E init_batch: failed to prepare attention ubatches
37.22.502.811 W decode: failed to find a memory slot for batch of size 66
37.22.502.813 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 33, ret = 1
37.22.509.504 E init_batch: failed to prepare attention ubatches
37.22.509.507 W decode: failed to find a memory slot for batch of size 33
37.22.509.508 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 16, ret = 1
37.22.516.570 E init_batch: failed to prepare attention ubatches
37.22.516.574 W decode: failed to find a memory slot for batch of size 16
37.22.516.575 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1973, n_batch = 8, ret = 1
37.22.728.093 E init_batch: failed to prepare attention ubatches
37.22.728.102 W decode: failed to find a memory slot for batch of size 6183
37.22.728.105 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 4250, ret = 1
37.22.736.392 E init_batch: failed to prepare attention ubatches
37.22.736.397 W decode: failed to find a memory slot for batch of size 4250
37.22.736.399 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 2125, ret = 1
37.22.743.693 E init_batch: failed to prepare attention ubatches
37.22.743.698 W decode: failed to find a memory slot for batch of size 2125
37.22.743.699 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 1062, ret = 1
37.22.750.975 E init_batch: failed to prepare attention ubatches
37.22.750.979 W decode: failed to find a memory slot for batch of size 1062
37.22.750.981 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 531, ret = 1
37.22.757.691 E init_batch: failed to prepare attention ubatches
37.22.757.696 W decode: failed to find a memory slot for batch of size 531
37.22.757.697 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 265, ret = 1
37.22.764.538 E init_batch: failed to prepare attention ubatches
37.22.764.542 W decode: failed to find a memory slot for batch of size 265
37.22.764.543 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 132, ret = 1
37.22.771.631 E init_batch: failed to prepare attention ubatches
37.22.771.637 W decode: failed to find a memory slot for batch of size 132
37.22.771.638 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 66, ret = 1
37.22.778.421 E init_batch: failed to prepare attention ubatches
37.22.778.425 W decode: failed to find a memory slot for batch of size 66
37.22.778.426 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 33, ret = 1
37.22.785.147 E init_batch: failed to prepare attention ubatches
37.22.785.151 W decode: failed to find a memory slot for batch of size 33
37.22.785.153 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 16, ret = 1
37.22.791.939 E init_batch: failed to prepare attention ubatches
37.22.791.944 W decode: failed to find a memory slot for batch of size 16
37.22.791.945 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 8, ret = 1
37.22.798.670 E init_batch: failed to prepare attention ubatches
37.22.798.674 W decode: failed to find a memory slot for batch of size 8
37.22.798.675 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 4, ret = 1
37.22.806.384 E init_batch: failed to prepare attention ubatches
37.22.806.390 W decode: failed to find a memory slot for batch of size 4
37.22.806.392 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 2, ret = 1
37.22.813.097 E init_batch: failed to prepare attention ubatches
37.22.813.102 W decode: failed to find a memory slot for batch of size 2
37.22.813.103 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1981, n_batch = 1, ret = 1
37.22.894.786 E init_batch: failed to prepare attention ubatches
37.22.894.794 W decode: failed to find a memory slot for batch of size 6182
37.22.894.797 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 4250, ret = 1
37.22.902.880 E init_batch: failed to prepare attention ubatches
37.22.902.884 W decode: failed to find a memory slot for batch of size 4250
37.22.902.885 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 2125, ret = 1
37.22.909.979 E init_batch: failed to prepare attention ubatches
37.22.909.983 W decode: failed to find a memory slot for batch of size 2125
37.22.909.984 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 1062, ret = 1
37.22.917.063 E init_batch: failed to prepare attention ubatches
37.22.917.067 W decode: failed to find a memory slot for batch of size 1062
37.22.917.068 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 531, ret = 1
37.22.923.813 E init_batch: failed to prepare attention ubatches
37.22.923.817 W decode: failed to find a memory slot for batch of size 531
37.22.923.819 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 265, ret = 1
37.22.930.442 E init_batch: failed to prepare attention ubatches
37.22.930.446 W decode: failed to find a memory slot for batch of size 265
37.22.930.447 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 132, ret = 1
37.22.937.234 E init_batch: failed to prepare attention ubatches
37.22.937.238 W decode: failed to find a memory slot for batch of size 132
37.22.937.239 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 66, ret = 1
37.22.944.033 E init_batch: failed to prepare attention ubatches
37.22.944.038 W decode: failed to find a memory slot for batch of size 66
37.22.944.040 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 33, ret = 1
37.22.950.272 E init_batch: failed to prepare attention ubatches
37.22.950.276 W decode: failed to find a memory slot for batch of size 33
37.22.950.277 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 16, ret = 1
37.22.957.027 E init_batch: failed to prepare attention ubatches
37.22.957.031 W decode: failed to find a memory slot for batch of size 16
37.22.957.032 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 8, ret = 1
37.22.963.744 E init_batch: failed to prepare attention ubatches
37.22.963.749 W decode: failed to find a memory slot for batch of size 8
37.22.963.768 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 4, ret = 1
37.22.970.612 E init_batch: failed to prepare attention ubatches
37.22.970.617 W decode: failed to find a memory slot for batch of size 4
37.22.970.619 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 2, ret = 1
37.22.977.489 E init_batch: failed to prepare attention ubatches
37.22.977.494 W decode: failed to find a memory slot for batch of size 2
37.22.977.496 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 1982, n_batch = 1, ret = 1
37.22.984.380 E init_batch: failed to prepare attention ubatches
37.22.984.385 W decode: failed to find a memory slot for batch of size 1
37.22.984.388 E srv decode: Context size has been exceeded. off = 1982, n_batch = 1, ret = 1
37.22.984.389 E srv send_error: task id = 2296, error: Context size has been exceeded.
37.22.984.399 I slot release: id 0 | task 2296 | stop processing: n_tokens = 70017, truncated = 0
37.22.984.500 W srv stop: cancel task, id_task = 2296
37.23.039.423 E srv send_error: task id = 2390, error: Context size has been exceeded.
37.23.039.453 I slot release: id 1 | task 2390 | stop processing: n_tokens = 5631, truncated = 0
37.23.039.512 W srv stop: cancel task, id_task = 2390
37.23.041.135 E srv send_error: task id = 2391, error: Context size has been exceeded.
37.23.041.141 I slot release: id 2 | task 2391 | stop processing: n_tokens = 138344, truncated = 0
37.23.041.227 W srv stop: cancel task, id_task = 2391
37.23.107.221 E srv send_error: task id = 2295, error: Context size has been exceeded.
37.23.107.231 I slot release: id 3 | task 2295 | stop processing: n_tokens = 54334, truncated = 0
37.23.107.313 W srv stop: cancel task, id_task = 2295
37.23.158.197 E srv update_slots: decode() failed: Context size has been exceeded.
37.23.826.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 20142088491
37.23.837.003 I slot launch_slot_: id 0 | task 2397 | processing task, is_child = 0
37.42.917.434 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 8500, progress = 0.06, t = 19.08 s / 445.50 tokens per second
38.03.086.153 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 17000, progress = 0.12, t = 39.25 s / 433.14 tokens per second
38.24.911.815 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 25500, progress = 0.17, t = 61.07 s / 417.53 tokens per second
38.43.147.059 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 30973, progress = 0.21, t = 79.31 s / 390.53 tokens per second
39.09.414.851 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 39473, progress = 0.27, t = 105.58 s / 373.88 tokens per second
39.37.035.980 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 47973, progress = 0.32, t = 133.20 s / 360.16 tokens per second
40.06.385.851 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 56473, progress = 0.38, t = 162.55 s / 347.42 tokens per second
40.36.884.015 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 64973, progress = 0.44, t = 193.05 s / 336.57 tokens per second
41.09.292.098 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 73473, progress = 0.50, t = 225.45 s / 325.89 tokens per second
41.42.878.071 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 81973, progress = 0.56, t = 259.04 s / 316.45 tokens per second
42.18.030.549 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 90473, progress = 0.61, t = 294.19 s / 307.53 tokens per second
42.54.376.349 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 98973, progress = 0.67, t = 330.54 s / 299.43 tokens per second
43.33.322.667 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 107473, progress = 0.73, t = 369.48 s / 290.87 tokens per second
44.13.159.341 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 115973, progress = 0.79, t = 409.32 s / 283.33 tokens per second
44.54.366.092 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 124473, progress = 0.84, t = 450.53 s / 276.28 tokens per second
45.37.390.828 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 132973, progress = 0.90, t = 493.55 s / 269.42 tokens per second
46.01.122.961 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 136307, progress = 0.92, t = 517.29 s / 263.50 tokens per second
46.22.936.462 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 139142, progress = 0.94, t = 539.10 s / 258.10 tokens per second
47.09.288.840 I slot print_timing: id 0 | task 2397 | prompt processing, n_tokens = 147638, progress = 1.00, t = 585.45 s / 252.18 tokens per second
47.15.705.092 I slot print_timing: id 0 | task 2397 | n_decoded = 100, tg = 16.19 t/s, tg_3s = 16.19 t/s
47.18.741.518 I slot print_timing: id 0 | task 2397 | n_decoded = 149, tg = 16.17 t/s, tg_3s = 16.14 t/s
47.21.787.657 I slot print_timing: id 0 | task 2397 | n_decoded = 198, tg = 16.15 t/s, tg_3s = 16.09 t/s
47.24.814.362 I slot print_timing: id 0 | task 2397 | n_decoded = 247, tg = 16.16 t/s, tg_3s = 16.19 t/s
47.27.826.677 I slot print_timing: id 0 | task 2397 | n_decoded = 294, tg = 16.07 t/s, tg_3s = 15.60 t/s
47.30.631.966 I slot print_timing: id 0 | task 2397 | prompt eval time = 585691.27 ms / 147642 tokens ( 3.97 ms per token, 252.08 tokens per second)
47.30.631.970 I slot print_timing: id 0 | task 2397 | eval time = 21103.00 ms / 338 tokens ( 62.43 ms per token, 16.02 tokens per second)
47.30.631.972 I slot print_timing: id 0 | task 2397 | total time = 606794.27 ms / 147980 tokens
47.30.631.974 I slot print_timing: id 0 | task 2397 | graphs reused = 2602
47.30.638.860 I slot release: id 0 | task 2397 | stop processing: n_tokens = 147979, truncated = 0
47.31.838.777 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.999
47.31.847.232 I slot launch_slot_: id 0 | task 2755 | processing task, is_child = 0
47.54.425.095 I slot print_timing: id 0 | task 2755 | prompt processing, n_tokens = 2842, progress = 0.95, t = 22.58 s / 125.89 tokens per second
48.42.781.376 I slot print_timing: id 0 | task 2755 | prompt processing, n_tokens = 11338, progress = 1.00, t = 70.93 s / 159.84 tokens per second
48.49.247.438 I slot print_timing: id 0 | task 2755 | n_decoded = 100, tg = 16.07 t/s, tg_3s = 16.07 t/s
48.52.278.310 I slot print_timing: id 0 | task 2755 | n_decoded = 148, tg = 16.00 t/s, tg_3s = 15.84 t/s
48.55.296.526 I slot print_timing: id 0 | task 2755 | n_decoded = 196, tg = 15.97 t/s, tg_3s = 15.90 t/s
48.58.313.732 I slot print_timing: id 0 | task 2755 | n_decoded = 244, tg = 15.96 t/s, tg_3s = 15.91 t/s
49.00.492.882 I slot print_timing: id 0 | task 2755 | prompt eval time = 71176.88 ms / 11342 tokens ( 6.28 ms per token, 159.35 tokens per second)
49.00.492.887 I slot print_timing: id 0 | task 2755 | eval time = 17467.03 ms / 278 tokens ( 62.83 ms per token, 15.92 tokens per second)
49.00.492.888 I slot print_timing: id 0 | task 2755 | total time = 88643.91 ms / 11620 tokens
49.00.492.890 I slot print_timing: id 0 | task 2755 | graphs reused = 2877
49.00.500.453 I slot release: id 0 | task 2755 | stop processing: n_tokens = 159257, truncated = 0
49.01.391.598 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.999
49.01.400.235 I slot launch_slot_: id 0 | task 3036 | processing task, is_child = 0
49.10.170.598 I slot print_timing: id 0 | task 3036 | prompt processing, n_tokens = 342, progress = 1.00, t = 8.77 s / 39.00 tokens per second
49.16.622.317 I slot print_timing: id 0 | task 3036 | n_decoded = 100, tg = 16.11 t/s, tg_3s = 16.11 t/s
49.19.643.773 I slot print_timing: id 0 | task 3036 | n_decoded = 145, tg = 15.71 t/s, tg_3s = 14.89 t/s
49.22.120.566 I slot print_timing: id 0 | task 3036 | prompt eval time = 9011.59 ms / 346 tokens ( 26.05 ms per token, 38.39 tokens per second)
49.22.120.571 I slot print_timing: id 0 | task 3036 | eval time = 11707.03 ms / 179 tokens ( 65.40 ms per token, 15.29 tokens per second)
49.22.120.572 I slot print_timing: id 0 | task 3036 | total time = 20718.62 ms / 525 tokens
49.22.120.573 I slot print_timing: id 0 | task 3036 | graphs reused = 3053
49.22.129.129 I slot release: id 0 | task 3036 | stop processing: n_tokens = 159500, truncated = 0
49.25.529.753 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
49.25.538.765 I slot launch_slot_: id 0 | task 3217 | processing task, is_child = 0
49.34.527.683 I slot print_timing: id 0 | task 3217 | prompt processing, n_tokens = 313, progress = 1.00, t = 8.99 s / 34.83 tokens per second
49.41.043.138 I slot print_timing: id 0 | task 3217 | n_decoded = 100, tg = 15.93 t/s, tg_3s = 15.93 t/s
49.44.043.613 I slot print_timing: id 0 | task 3217 | n_decoded = 147, tg = 15.84 t/s, tg_3s = 15.66 t/s
49.44.442.283 I slot print_timing: id 0 | task 3217 | prompt eval time = 9224.00 ms / 317 tokens ( 29.10 ms per token, 34.37 tokens per second)
49.44.442.287 I slot print_timing: id 0 | task 3217 | eval time = 9677.82 ms / 153 tokens ( 63.25 ms per token, 15.81 tokens per second)
49.44.442.289 I slot print_timing: id 0 | task 3217 | total time = 18901.82 ms / 470 tokens
49.44.442.290 I slot print_timing: id 0 | task 3217 | graphs reused = 3203
49.44.449.652 I slot release: id 0 | task 3217 | stop processing: n_tokens = 159787, truncated = 0
49.45.596.706 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 1.000
49.45.605.788 I slot launch_slot_: id 0 | task 3372 | processing task, is_child = 0
50.04.491.209 I slot print_timing: id 0 | task 3372 | prompt processing, n_tokens = 2011, progress = 0.95, t = 18.88 s / 106.49 tokens per second
50.55.118.956 I slot print_timing: id 0 | task 3372 | prompt processing, n_tokens = 10507, progress = 1.00, t = 69.51 s / 151.15 tokens per second
51.01.718.267 I slot print_timing: id 0 | task 3372 | n_decoded = 100, tg = 15.74 t/s, tg_3s = 15.74 t/s
51.04.759.127 I slot print_timing: id 0 | task 3372 | n_decoded = 146, tg = 15.54 t/s, tg_3s = 15.13 t/s
51.07.762.599 I slot print_timing: id 0 | task 3372 | n_decoded = 193, tg = 15.57 t/s, tg_3s = 15.65 t/s
51.10.796.413 I slot print_timing: id 0 | task 3372 | n_decoded = 240, tg = 15.55 t/s, tg_3s = 15.49 t/s
51.11.897.117 I slot print_timing: id 0 | task 3372 | prompt eval time = 69758.08 ms / 10511 tokens ( 6.64 ms per token, 150.68 tokens per second)
51.11.897.122 I slot print_timing: id 0 | task 3372 | eval time = 16531.64 ms / 257 tokens ( 64.33 ms per token, 15.55 tokens per second)
51.11.897.123 I slot print_timing: id 0 | task 3372 | total time = 86289.72 ms / 10768 tokens
51.11.897.125 I slot print_timing: id 0 | task 3372 | graphs reused = 3457
51.11.905.512 I slot release: id 0 | task 3372 | stop processing: n_tokens = 170398, truncated = 0
51.13.484.485 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.968 (> 0.100 thold), f_keep = 0.999
51.13.493.723 I slot launch_slot_: id 0 | task 3632 | processing task, is_child = 0
51.52.318.281 I slot print_timing: id 0 | task 3632 | prompt processing, n_tokens = 5721, progress = 1.00, t = 38.82 s / 147.36 tokens per second
51.58.950.150 I slot print_timing: id 0 | task 3632 | n_decoded = 100, tg = 15.64 t/s, tg_3s = 15.64 t/s
52.01.980.187 I slot print_timing: id 0 | task 3632 | n_decoded = 146, tg = 15.49 t/s, tg_3s = 15.18 t/s
52.05.012.875 I slot print_timing: id 0 | task 3632 | n_decoded = 190, tg = 15.25 t/s, tg_3s = 14.51 t/s
52.08.036.572 I slot print_timing: id 0 | task 3632 | n_decoded = 236, tg = 15.24 t/s, tg_3s = 15.21 t/s
52.08.926.789 I slot print_timing: id 0 | task 3632 | prompt eval time = 39060.05 ms / 5725 tokens ( 6.82 ms per token, 146.57 tokens per second)
52.08.926.793 I slot print_timing: id 0 | task 3632 | eval time = 16371.29 ms / 250 tokens ( 65.49 ms per token, 15.27 tokens per second)
52.08.926.795 I slot print_timing: id 0 | task 3632 | total time = 55431.35 ms / 5975 tokens
52.08.926.796 I slot print_timing: id 0 | task 3632 | graphs reused = 3704
52.08.935.068 I slot release: id 0 | task 3632 | stop processing: n_tokens = 176112, truncated = 0
52.15.031.653 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
52.15.040.663 I slot launch_slot_: id 0 | task 3884 | processing task, is_child = 0
52.24.745.899 I slot print_timing: id 0 | task 3884 | prompt processing, n_tokens = 376, progress = 1.00, t = 9.70 s / 38.75 tokens per second
52.31.490.192 I slot print_timing: id 0 | task 3884 | n_decoded = 100, tg = 15.39 t/s, tg_3s = 15.39 t/s
52.34.550.438 I slot print_timing: id 0 | task 3884 | n_decoded = 145, tg = 15.17 t/s, tg_3s = 14.70 t/s
52.37.567.111 I slot print_timing: id 0 | task 3884 | n_decoded = 187, tg = 14.87 t/s, tg_3s = 13.92 t/s
52.39.162.947 I slot print_timing: id 0 | task 3884 | prompt eval time = 9948.12 ms / 380 tokens ( 26.18 ms per token, 38.20 tokens per second)
52.39.162.953 I slot print_timing: id 0 | task 3884 | eval time = 14172.39 ms / 211 tokens ( 67.17 ms per token, 14.89 tokens per second)
52.39.162.954 I slot print_timing: id 0 | task 3884 | total time = 24120.51 ms / 591 tokens
52.39.162.956 I slot print_timing: id 0 | task 3884 | graphs reused = 3912
52.39.171.124 I slot release: id 0 | task 3884 | stop processing: n_tokens = 176449, truncated = 0
52.40.130.992 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.999
52.40.139.929 I slot launch_slot_: id 0 | task 4097 | processing task, is_child = 0
52.49.533.476 I slot print_timing: id 0 | task 4097 | prompt processing, n_tokens = 312, progress = 1.00, t = 9.39 s / 33.22 tokens per second
52.56.206.757 I slot print_timing: id 0 | task 4097 | n_decoded = 100, tg = 15.55 t/s, tg_3s = 15.55 t/s
52.58.689.895 I slot print_timing: id 0 | task 4097 | prompt eval time = 9634.16 ms / 316 tokens ( 30.49 ms per token, 32.80 tokens per second)
52.58.689.899 I slot print_timing: id 0 | task 4097 | eval time = 8913.99 ms / 138 tokens ( 64.59 ms per token, 15.48 tokens per second)
52.58.689.900 I slot print_timing: id 0 | task 4097 | total time = 18548.15 ms / 454 tokens
52.58.689.902 I slot print_timing: id 0 | task 4097 | graphs reused = 4047
52.58.697.663 I slot release: id 0 | task 4097 | stop processing: n_tokens = 176688, truncated = 0
52.59.794.829 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.993 (> 0.100 thold), f_keep = 1.000
52.59.803.924 I slot launch_slot_: id 0 | task 4237 | processing task, is_child = 0
53.15.878.746 I slot print_timing: id 0 | task 4237 | prompt processing, n_tokens = 1215, progress = 1.00, t = 16.07 s / 75.59 tokens per second
53.22.481.778 I slot print_timing: id 0 | task 4237 | n_decoded = 100, tg = 15.73 t/s, tg_3s = 15.73 t/s
53.25.515.341 I slot print_timing: id 0 | task 4237 | n_decoded = 147, tg = 15.65 t/s, tg_3s = 15.49 t/s
53.28.560.782 I slot print_timing: id 0 | task 4237 | n_decoded = 194, tg = 15.60 t/s, tg_3s = 15.43 t/s
53.31.603.127 I slot print_timing: id 0 | task 4237 | n_decoded = 241, tg = 15.57 t/s, tg_3s = 15.45 t/s
53.34.637.312 I slot print_timing: id 0 | task 4237 | n_decoded = 288, tg = 15.56 t/s, tg_3s = 15.49 t/s
53.37.679.797 I slot print_timing: id 0 | task 4237 | n_decoded = 335, tg = 15.54 t/s, tg_3s = 15.45 t/s
53.40.682.387 I slot print_timing: id 0 | task 4237 | n_decoded = 382, tg = 15.55 t/s, tg_3s = 15.65 t/s
53.43.737.839 I slot print_timing: id 0 | task 4237 | n_decoded = 429, tg = 15.54 t/s, tg_3s = 15.38 t/s
53.46.756.585 I slot print_timing: id 0 | task 4237 | n_decoded = 476, tg = 15.54 t/s, tg_3s = 15.57 t/s
53.49.772.145 I slot print_timing: id 0 | task 4237 | n_decoded = 523, tg = 15.54 t/s, tg_3s = 15.59 t/s
53.52.792.933 I slot print_timing: id 0 | task 4237 | n_decoded = 570, tg = 15.54 t/s, tg_3s = 15.56 t/s
53.55.801.390 I slot print_timing: id 0 | task 4237 | n_decoded = 617, tg = 15.55 t/s, tg_3s = 15.62 t/s
53.58.856.865 I slot print_timing: id 0 | task 4237 | n_decoded = 665, tg = 15.56 t/s, tg_3s = 15.71 t/s
54.01.876.053 I slot print_timing: id 0 | task 4237 | n_decoded = 712, tg = 15.56 t/s, tg_3s = 15.57 t/s
54.04.889.513 I slot print_timing: id 0 | task 4237 | n_decoded = 759, tg = 15.56 t/s, tg_3s = 15.60 t/s
54.07.918.625 I slot print_timing: id 0 | task 4237 | n_decoded = 806, tg = 15.56 t/s, tg_3s = 15.52 t/s
54.10.931.081 I slot print_timing: id 0 | task 4237 | n_decoded = 853, tg = 15.56 t/s, tg_3s = 15.60 t/s
54.13.946.032 I slot print_timing: id 0 | task 4237 | n_decoded = 900, tg = 15.56 t/s, tg_3s = 15.59 t/s
54.16.966.644 I slot print_timing: id 0 | task 4237 | n_decoded = 947, tg = 15.56 t/s, tg_3s = 15.56 t/s
54.19.996.321 I slot print_timing: id 0 | task 4237 | n_decoded = 994, tg = 15.56 t/s, tg_3s = 15.51 t/s
54.23.038.766 I slot print_timing: id 0 | task 4237 | n_decoded = 1041, tg = 15.56 t/s, tg_3s = 15.45 t/s
54.26.092.213 I slot print_timing: id 0 | task 4237 | n_decoded = 1086, tg = 15.52 t/s, tg_3s = 14.74 t/s
54.29.096.826 I slot print_timing: id 0 | task 4237 | n_decoded = 1132, tg = 15.51 t/s, tg_3s = 15.31 t/s
54.29.792.636 I slot print_timing: id 0 | task 4237 | prompt eval time = 16317.83 ms / 1219 tokens ( 13.39 ms per token, 74.70 tokens per second)
54.29.792.641 I slot print_timing: id 0 | task 4237 | eval time = 73668.93 ms / 1141 tokens ( 64.57 ms per token, 15.49 tokens per second)
54.29.792.642 I slot print_timing: id 0 | task 4237 | total time = 89986.76 ms / 2360 tokens
54.29.792.643 I slot print_timing: id 0 | task 4237 | graphs reused = 5182
54.29.800.675 I slot release: id 0 | task 4237 | stop processing: n_tokens = 178906, truncated = 0
54.31.649.255 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.999
54.31.657.386 I slot launch_slot_: id 0 | task 5380 | processing task, is_child = 0
54.47.984.406 I slot print_timing: id 0 | task 5380 | prompt processing, n_tokens = 1264, progress = 1.00, t = 16.33 s / 77.43 tokens per second
54.54.673.091 I slot print_timing: id 0 | task 5380 | n_decoded = 100, tg = 15.50 t/s, tg_3s = 15.50 t/s
54.56.282.590 I slot print_timing: id 0 | task 5380 | prompt eval time = 16561.49 ms / 1268 tokens ( 13.06 ms per token, 76.56 tokens per second)
54.56.282.595 I slot print_timing: id 0 | task 5380 | eval time = 8061.97 ms / 124 tokens ( 65.02 ms per token, 15.38 tokens per second)
54.56.282.597 I slot print_timing: id 0 | task 5380 | total time = 24623.46 ms / 1392 tokens
54.56.282.603 I slot print_timing: id 0 | task 5380 | graphs reused = 5304
54.56.290.568 I slot release: id 0 | task 5380 | stop processing: n_tokens = 179153, truncated = 0
54.57.174.309 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 1.000
54.57.182.776 I slot launch_slot_: id 0 | task 5506 | processing task, is_child = 0
55.09.028.607 I slot print_timing: id 0 | task 5506 | prompt processing, n_tokens = 580, progress = 1.00, t = 11.84 s / 48.97 tokens per second
55.15.695.559 I slot print_timing: id 0 | task 5506 | n_decoded = 100, tg = 15.55 t/s, tg_3s = 15.55 t/s
55.18.703.575 I slot print_timing: id 0 | task 5506 | n_decoded = 146, tg = 15.47 t/s, tg_3s = 15.29 t/s
55.18.925.961 I slot print_timing: id 0 | task 5506 | prompt eval time = 12081.38 ms / 584 tokens ( 20.69 ms per token, 48.34 tokens per second)
55.18.925.966 I slot print_timing: id 0 | task 5506 | eval time = 9660.08 ms / 149 tokens ( 64.83 ms per token, 15.42 tokens per second)
55.18.925.967 I slot print_timing: id 0 | task 5506 | total time = 21741.46 ms / 733 tokens
55.18.925.969 I slot print_timing: id 0 | task 5506 | graphs reused = 5450
55.18.934.186 I slot release: id 0 | task 5506 | stop processing: n_tokens = 179758, truncated = 0
55.20.710.150 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.999
55.20.718.751 I slot launch_slot_: id 0 | task 5657 | processing task, is_child = 0
55.29.685.131 I slot print_timing: id 0 | task 5657 | prompt processing, n_tokens = 277, progress = 1.00, t = 8.96 s / 30.90 tokens per second
55.36.371.782 I slot print_timing: id 0 | task 5657 | n_decoded = 100, tg = 15.53 t/s, tg_3s = 15.53 t/s
55.39.415.557 I slot print_timing: id 0 | task 5657 | n_decoded = 147, tg = 15.50 t/s, tg_3s = 15.44 t/s
55.42.459.607 I slot print_timing: id 0 | task 5657 | n_decoded = 194, tg = 15.49 t/s, tg_3s = 15.44 t/s
55.45.508.718 I slot print_timing: id 0 | task 5657 | n_decoded = 241, tg = 15.47 t/s, tg_3s = 15.41 t/s
55.48.545.346 I slot print_timing: id 0 | task 5657 | n_decoded = 288, tg = 15.47 t/s, tg_3s = 15.48 t/s
55.51.584.663 I slot print_timing: id 0 | task 5657 | n_decoded = 335, tg = 15.47 t/s, tg_3s = 15.46 t/s
55.54.591.945 I slot print_timing: id 0 | task 5657 | n_decoded = 382, tg = 15.49 t/s, tg_3s = 15.63 t/s
55.57.632.302 I slot print_timing: id 0 | task 5657 | n_decoded = 429, tg = 15.49 t/s, tg_3s = 15.46 t/s
56.00.648.164 I slot print_timing: id 0 | task 5657 | n_decoded = 476, tg = 15.50 t/s, tg_3s = 15.58 t/s
56.03.648.449 I slot print_timing: id 0 | task 5657 | n_decoded = 523, tg = 15.51 t/s, tg_3s = 15.67 t/s
56.06.706.093 I slot print_timing: id 0 | task 5657 | n_decoded = 571, tg = 15.53 t/s, tg_3s = 15.70 t/s
56.09.723.022 I slot print_timing: id 0 | task 5657 | n_decoded = 618, tg = 15.53 t/s, tg_3s = 15.58 t/s
56.12.737.324 I slot print_timing: id 0 | task 5657 | n_decoded = 665, tg = 15.54 t/s, tg_3s = 15.59 t/s
56.15.771.112 I slot print_timing: id 0 | task 5657 | n_decoded = 712, tg = 15.53 t/s, tg_3s = 15.49 t/s
56.18.794.669 I slot print_timing: id 0 | task 5657 | n_decoded = 759, tg = 15.53 t/s, tg_3s = 15.54 t/s
56.21.818.832 I slot print_timing: id 0 | task 5657 | n_decoded = 806, tg = 15.53 t/s, tg_3s = 15.54 t/s
56.24.874.435 I slot print_timing: id 0 | task 5657 | n_decoded = 853, tg = 15.53 t/s, tg_3s = 15.38 t/s
56.27.917.589 I slot print_timing: id 0 | task 5657 | n_decoded = 900, tg = 15.52 t/s, tg_3s = 15.44 t/s
56.30.972.762 I slot print_timing: id 0 | task 5657 | n_decoded = 947, tg = 15.51 t/s, tg_3s = 15.38 t/s
56.34.017.169 I slot print_timing: id 0 | task 5657 | n_decoded = 994, tg = 15.51 t/s, tg_3s = 15.44 t/s
56.37.000.952 I slot print_timing: id 0 | task 5657 | prompt eval time = 9212.69 ms / 281 tokens ( 32.79 ms per token, 30.50 tokens per second)
56.37.000.959 I slot print_timing: id 0 | task 5657 | eval time = 67067.65 ms / 1038 tokens ( 64.61 ms per token, 15.48 tokens per second)
56.37.000.961 I slot print_timing: id 0 | task 5657 | total time = 76280.34 ms / 1319 tokens
56.37.000.962 I slot print_timing: id 0 | task 5657 | graphs reused = 6482
56.37.009.156 I slot release: id 0 | task 5657 | stop processing: n_tokens = 180924, truncated = 0
56.38.026.294 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.994 (> 0.100 thold), f_keep = 1.000
56.38.034.935 I slot launch_slot_: id 0 | task 6697 | processing task, is_child = 0
56.59.431.430 I slot print_timing: id 0 | task 6697 | prompt processing, n_tokens = 2084, progress = 1.00, t = 21.39 s / 97.41 tokens per second
57.06.158.310 I slot print_timing: id 0 | task 6697 | n_decoded = 100, tg = 15.42 t/s, tg_3s = 15.42 t/s
57.06.571.365 I slot print_timing: id 0 | task 6697 | prompt eval time = 21637.28 ms / 2088 tokens ( 10.36 ms per token, 96.50 tokens per second)
57.06.571.371 I slot print_timing: id 0 | task 6697 | eval time = 6897.44 ms / 106 tokens ( 65.07 ms per token, 15.37 tokens per second)
57.06.571.373 I slot print_timing: id 0 | task 6697 | total time = 28534.72 ms / 2194 tokens
57.06.571.375 I slot print_timing: id 0 | task 6697 | graphs reused = 6585
57.06.579.624 I slot release: id 0 | task 6697 | stop processing: n_tokens = 182076, truncated = 0
57.09.430.705 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
57.09.439.081 I slot launch_slot_: id 0 | task 6805 | processing task, is_child = 0
57.18.901.531 I slot print_timing: id 0 | task 6805 | prompt processing, n_tokens = 305, progress = 1.00, t = 9.46 s / 32.24 tokens per second
57.24.315.886 I slot print_timing: id 0 | task 6805 | prompt eval time = 9697.59 ms / 309 tokens ( 31.38 ms per token, 31.86 tokens per second)
57.24.315.892 I slot print_timing: id 0 | task 6805 | eval time = 5177.53 ms / 79 tokens ( 65.54 ms per token, 15.26 tokens per second)
57.24.315.893 I slot print_timing: id 0 | task 6805 | total time = 14875.13 ms / 388 tokens
57.24.315.895 I slot print_timing: id 0 | task 6805 | graphs reused = 6662
57.24.324.272 I slot release: id 0 | task 6805 | stop processing: n_tokens = 182354, truncated = 0
57.25.343.081 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 1.000
57.25.351.717 I slot launch_slot_: id 0 | task 6886 | processing task, is_child = 0
57.31.309.763 I slot print_timing: id 0 | task 6886 | prompt processing, n_tokens = 104, progress = 1.00, t = 5.96 s / 17.46 tokens per second
57.38.089.447 I slot print_timing: id 0 | task 6886 | n_decoded = 100, tg = 15.31 t/s, tg_3s = 15.31 t/s
57.41.143.964 I slot print_timing: id 0 | task 6886 | n_decoded = 147, tg = 15.34 t/s, tg_3s = 15.39 t/s
57.44.145.519 I slot print_timing: id 0 | task 6886 | n_decoded = 193, tg = 15.33 t/s, tg_3s = 15.33 t/s
57.47.168.559 I slot print_timing: id 0 | task 6886 | n_decoded = 239, tg = 15.31 t/s, tg_3s = 15.22 t/s
57.50.211.305 I slot print_timing: id 0 | task 6886 | n_decoded = 286, tg = 15.33 t/s, tg_3s = 15.45 t/s
57.53.258.572 I slot print_timing: id 0 | task 6886 | n_decoded = 333, tg = 15.35 t/s, tg_3s = 15.42 t/s
57.56.302.717 I slot print_timing: id 0 | task 6886 | n_decoded = 380, tg = 15.36 t/s, tg_3s = 15.44 t/s
57.59.359.549 I slot print_timing: id 0 | task 6886 | n_decoded = 427, tg = 15.36 t/s, tg_3s = 15.38 t/s
58.02.389.949 I slot print_timing: id 0 | task 6886 | n_decoded = 474, tg = 15.37 t/s, tg_3s = 15.51 t/s
58.05.428.769 I slot print_timing: id 0 | task 6886 | n_decoded = 521, tg = 15.38 t/s, tg_3s = 15.47 t/s
58.08.469.084 I slot print_timing: id 0 | task 6886 | n_decoded = 568, tg = 15.39 t/s, tg_3s = 15.46 t/s
58.11.514.094 I slot print_timing: id 0 | task 6886 | n_decoded = 615, tg = 15.39 t/s, tg_3s = 15.44 t/s
58.14.564.813 I slot print_timing: id 0 | task 6886 | n_decoded = 662, tg = 15.39 t/s, tg_3s = 15.41 t/s
58.17.620.092 I slot print_timing: id 0 | task 6886 | n_decoded = 709, tg = 15.39 t/s, tg_3s = 15.38 t/s
58.20.686.950 I slot print_timing: id 0 | task 6886 | n_decoded = 756, tg = 15.39 t/s, tg_3s = 15.33 t/s
58.23.691.723 I slot print_timing: id 0 | task 6886 | n_decoded = 802, tg = 15.38 t/s, tg_3s = 15.31 t/s
58.26.755.840 I slot print_timing: id 0 | task 6886 | n_decoded = 849, tg = 15.38 t/s, tg_3s = 15.34 t/s
58.29.820.719 I slot print_timing: id 0 | task 6886 | n_decoded = 896, tg = 15.38 t/s, tg_3s = 15.33 t/s
58.32.880.545 I slot print_timing: id 0 | task 6886 | n_decoded = 943, tg = 15.38 t/s, tg_3s = 15.36 t/s
58.35.892.117 I slot print_timing: id 0 | task 6886 | n_decoded = 990, tg = 15.39 t/s, tg_3s = 15.61 t/s
58.38.932.054 I slot print_timing: id 0 | task 6886 | n_decoded = 1037, tg = 15.39 t/s, tg_3s = 15.46 t/s
58.39.966.084 I slot print_timing: id 0 | task 6886 | prompt eval time = 6206.28 ms / 108 tokens ( 57.47 ms per token, 17.40 tokens per second)
58.39.966.089 I slot print_timing: id 0 | task 6886 | eval time = 68406.25 ms / 1053 tokens ( 64.96 ms per token, 15.39 tokens per second)
58.39.966.090 I slot print_timing: id 0 | task 6886 | total time = 74612.54 ms / 1161 tokens
58.39.966.091 I slot print_timing: id 0 | task 6886 | graphs reused = 7709
58.39.974.154 I slot release: id 0 | task 6886 | stop processing: n_tokens = 183432, truncated = 0
58.41.005.936 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 1.000
58.41.014.521 I slot launch_slot_: id 0 | task 7941 | processing task, is_child = 0
58.41.176.525 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 20142143546
58.41.184.407 I slot launch_slot_: id 1 | task 7943 | processing task, is_child = 0
59.44.354.957 I slot print_timing: id 0 | task 7941 | prompt processing, n_tokens = 353, progress = 1.00, t = 63.34 s / 5.57 tokens per second
59.44.478.549 I slot print_timing: id 1 | task 7943 | prompt processing, n_tokens = 8148, progress = 0.04, t = 63.22 s / 128.88 tokens per second
60.40.192.548 I slot print_timing: id 1 | task 7943 | prompt processing, n_tokens = 16644, progress = 0.09, t = 118.93 s / 139.94 tokens per second
61.37.227.523 I slot print_timing: id 1 | task 7943 | prompt processing, n_tokens = 25143, progress = 0.14, t = 175.97 s / 142.88 tokens per second
62.20.453.084 I slot print_timing: id 1 | task 7943 | prompt processing, n_tokens = 30973, progress = 0.17, t = 219.19 s / 141.30 tokens per second
63.21.806.848 I slot print_timing: id 1 | task 7943 | prompt processing, n_tokens = 39472, progress = 0.22, t = 280.55 s / 140.70 tokens per second
64.24.725.428 I slot print_timing: id 1 | task 7943 | prompt processing, n_tokens = 47971, progress = 0.26, t = 343.47 s / 139.67 tokens per second
65.29.637.132 I slot print_timing: id 1 | task 7943 | prompt processing, n_tokens = 56470, progress = 0.31, t = 408.38 s / 138.28 tokens per second
66.35.601.728 I slot print_timing: id 1 | task 7943 | prompt processing, n_tokens = 64969, progress = 0.35, t = 474.34 s / 136.97 tokens per second
67.43.535.432 I slot print_timing: id 1 | task 7943 | prompt processing, n_tokens = 73468, progress = 0.40, t = 542.28 s / 135.48 tokens per second
67.43.545.647 E init_batch: failed to prepare attention ubatches
67.43.545.652 W decode: failed to find a memory slot for batch of size 8500
67.43.545.654 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 0, n_batch = 4250, ret = 1
68.22.673.293 E init_batch: failed to prepare attention ubatches
68.22.673.301 W decode: failed to find a memory slot for batch of size 4250
68.22.673.321 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4250, n_batch = 4250, ret = 1
68.22.681.237 E init_batch: failed to prepare attention ubatches
68.22.681.244 W decode: failed to find a memory slot for batch of size 4250
68.22.681.246 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4250, n_batch = 2125, ret = 1
68.22.688.940 E init_batch: failed to prepare attention ubatches
68.22.688.944 W decode: failed to find a memory slot for batch of size 2125
68.22.688.945 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4250, n_batch = 1062, ret = 1
68.22.696.209 E init_batch: failed to prepare attention ubatches
68.22.696.213 W decode: failed to find a memory slot for batch of size 1062
68.22.696.215 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4250, n_batch = 531, ret = 1
68.33.288.823 E init_batch: failed to prepare attention ubatches
68.33.288.833 W decode: failed to find a memory slot for batch of size 3719
68.33.288.837 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4781, n_batch = 4250, ret = 1
68.33.296.672 E init_batch: failed to prepare attention ubatches
68.33.296.676 W decode: failed to find a memory slot for batch of size 3719
68.33.296.678 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4781, n_batch = 2125, ret = 1
68.33.303.961 E init_batch: failed to prepare attention ubatches
68.33.303.965 W decode: failed to find a memory slot for batch of size 2125
68.33.303.966 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4781, n_batch = 1062, ret = 1
68.33.310.805 E init_batch: failed to prepare attention ubatches
68.33.310.808 W decode: failed to find a memory slot for batch of size 1062
68.33.310.809 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4781, n_batch = 531, ret = 1
68.33.317.607 E init_batch: failed to prepare attention ubatches
68.33.317.611 W decode: failed to find a memory slot for batch of size 531
68.33.317.612 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4781, n_batch = 265, ret = 1
68.33.324.443 E init_batch: failed to prepare attention ubatches
68.33.324.447 W decode: failed to find a memory slot for batch of size 265
68.33.324.448 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4781, n_batch = 132, ret = 1
68.33.331.234 E init_batch: failed to prepare attention ubatches
68.33.331.238 W decode: failed to find a memory slot for batch of size 132
68.33.331.239 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4781, n_batch = 66, ret = 1
68.37.138.632 E init_batch: failed to prepare attention ubatches
68.37.138.639 W decode: failed to find a memory slot for batch of size 3653
68.37.138.643 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4847, n_batch = 4250, ret = 1
68.37.146.216 E init_batch: failed to prepare attention ubatches
68.37.146.220 W decode: failed to find a memory slot for batch of size 3653
68.37.146.237 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4847, n_batch = 2125, ret = 1
68.37.153.502 E init_batch: failed to prepare attention ubatches
68.37.153.506 W decode: failed to find a memory slot for batch of size 2125
68.37.153.507 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4847, n_batch = 1062, ret = 1
68.37.160.415 E init_batch: failed to prepare attention ubatches
68.37.160.419 W decode: failed to find a memory slot for batch of size 1062
68.37.160.420 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4847, n_batch = 531, ret = 1
68.37.167.159 E init_batch: failed to prepare attention ubatches
68.37.167.163 W decode: failed to find a memory slot for batch of size 531
68.37.167.165 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4847, n_batch = 265, ret = 1
68.37.173.966 E init_batch: failed to prepare attention ubatches
68.37.173.970 W decode: failed to find a memory slot for batch of size 265
68.37.173.971 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4847, n_batch = 132, ret = 1
68.37.180.471 E init_batch: failed to prepare attention ubatches
68.37.180.475 W decode: failed to find a memory slot for batch of size 132
68.37.180.476 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4847, n_batch = 66, ret = 1
68.37.187.170 E init_batch: failed to prepare attention ubatches
68.37.187.174 W decode: failed to find a memory slot for batch of size 66
68.37.187.175 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4847, n_batch = 33, ret = 1
68.39.995.561 E init_batch: failed to prepare attention ubatches
68.39.995.569 W decode: failed to find a memory slot for batch of size 3620
68.39.995.572 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 4250, ret = 1
68.40.002.823 E init_batch: failed to prepare attention ubatches
68.40.002.827 W decode: failed to find a memory slot for batch of size 3620
68.40.002.829 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 2125, ret = 1
68.40.010.029 E init_batch: failed to prepare attention ubatches
68.40.010.033 W decode: failed to find a memory slot for batch of size 2125
68.40.010.035 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 1062, ret = 1
68.40.016.786 E init_batch: failed to prepare attention ubatches
68.40.016.791 W decode: failed to find a memory slot for batch of size 1062
68.40.016.792 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 531, ret = 1
68.40.023.396 E init_batch: failed to prepare attention ubatches
68.40.023.400 W decode: failed to find a memory slot for batch of size 531
68.40.023.402 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 265, ret = 1
68.40.030.023 E init_batch: failed to prepare attention ubatches
68.40.030.027 W decode: failed to find a memory slot for batch of size 265
68.40.030.028 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 132, ret = 1
68.40.036.613 E init_batch: failed to prepare attention ubatches
68.40.036.617 W decode: failed to find a memory slot for batch of size 132
68.40.036.619 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 66, ret = 1
68.40.043.133 E init_batch: failed to prepare attention ubatches
68.40.043.137 W decode: failed to find a memory slot for batch of size 66
68.40.043.138 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 33, ret = 1
68.40.049.537 E init_batch: failed to prepare attention ubatches
68.40.049.542 W decode: failed to find a memory slot for batch of size 33
68.40.049.544 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 16, ret = 1
68.40.056.050 E init_batch: failed to prepare attention ubatches
68.40.056.053 W decode: failed to find a memory slot for batch of size 16
68.40.056.054 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 8, ret = 1
68.40.062.557 E init_batch: failed to prepare attention ubatches
68.40.062.560 W decode: failed to find a memory slot for batch of size 8
68.40.062.561 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 4, ret = 1
68.40.069.177 E init_batch: failed to prepare attention ubatches
68.40.069.180 W decode: failed to find a memory slot for batch of size 4
68.40.069.182 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 2, ret = 1
68.40.075.643 E init_batch: failed to prepare attention ubatches
68.40.075.646 W decode: failed to find a memory slot for batch of size 2
68.40.075.647 W srv decode: failed to find free space in the KV cache, retrying with smaller batch size, off = 4880, n_batch = 1, ret = 1
68.40.082.269 E init_batch: failed to prepare attention ubatches
68.40.082.272 W decode: failed to find a memory slot for batch of size 1
68.40.082.275 E srv decode: Context size has been exceeded. off = 4880, n_batch = 1, ret = 1
68.40.082.276 E srv send_error: task id = 7941, error: Context size has been exceeded.
68.40.082.301 I slot release: id 0 | task 7941 | stop processing: n_tokens = 183797, truncated = 0
68.40.082.369 W srv stop: cancel task, id_task = 7941
68.40.180.970 E srv send_error: task id = 7943, error: Context size has been exceeded.
68.40.180.981 I slot release: id 1 | task 7943 | stop processing: n_tokens = 81967, truncated = 0
68.40.181.077 W srv stop: cancel task, id_task = 7943
68.40.201.903 E srv update_slots: decode() failed: Context size has been exceeded.
81.12.428.535 I slot get_availabl: id 2 | task -1 | selected slot by LRU, t_last = 20142145233
81.12.440.333 I slot launch_slot_: id 2 | task 7956 | processing task, is_child = 0
81.31.600.460 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 8500, progress = 0.05, t = 19.16 s / 443.64 tokens per second
81.51.852.644 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 17000, progress = 0.09, t = 39.41 s / 431.34 tokens per second
82.13.943.992 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 25500, progress = 0.14, t = 61.50 s / 414.61 tokens per second
82.32.289.360 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 30973, progress = 0.17, t = 79.85 s / 387.90 tokens per second
82.58.785.094 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 39473, progress = 0.22, t = 106.34 s / 371.18 tokens per second
83.26.651.476 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 47973, progress = 0.26, t = 134.21 s / 357.45 tokens per second
83.56.162.986 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 56473, progress = 0.31, t = 163.72 s / 344.93 tokens per second
84.26.859.959 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 64973, progress = 0.35, t = 194.42 s / 334.19 tokens per second
84.59.489.470 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 73473, progress = 0.40, t = 227.05 s / 323.60 tokens per second
85.33.338.328 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 81973, progress = 0.45, t = 260.90 s / 314.20 tokens per second
86.08.704.229 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 90473, progress = 0.49, t = 296.26 s / 305.38 tokens per second
86.45.293.136 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 98973, progress = 0.54, t = 332.85 s / 297.35 tokens per second
87.24.473.511 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 107473, progress = 0.59, t = 372.03 s / 288.88 tokens per second
88.04.636.327 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 115973, progress = 0.63, t = 412.20 s / 281.35 tokens per second
88.46.192.516 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 124473, progress = 0.68, t = 453.75 s / 274.32 tokens per second
89.29.519.264 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 132973, progress = 0.72, t = 497.08 s / 267.51 tokens per second
89.53.426.782 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 136307, progress = 0.74, t = 520.99 s / 261.63 tokens per second
90.39.507.410 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 144807, progress = 0.79, t = 567.07 s / 255.36 tokens per second
91.27.407.640 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 153307, progress = 0.84, t = 614.97 s / 249.29 tokens per second
92.16.808.092 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 161807, progress = 0.88, t = 664.37 s / 243.55 tokens per second
93.07.299.099 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 170307, progress = 0.93, t = 714.86 s / 238.24 tokens per second
93.40.347.037 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 174975, progress = 0.95, t = 747.91 s / 233.95 tokens per second
94.34.186.428 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 183433, progress = 1.00, t = 801.75 s / 228.79 tokens per second
94.36.707.711 I slot print_timing: id 2 | task 7956 | prompt processing, n_tokens = 183471, progress = 1.00, t = 804.27 s / 228.12 tokens per second
94.43.415.613 I slot print_timing: id 2 | task 7956 | n_decoded = 100, tg = 15.49 t/s, tg_3s = 15.49 t/s
94.46.447.428 I slot print_timing: id 2 | task 7956 | n_decoded = 147, tg = 15.49 t/s, tg_3s = 15.50 t/s
94.49.503.261 I slot print_timing: id 2 | task 7956 | n_decoded = 194, tg = 15.47 t/s, tg_3s = 15.38 t/s
94.52.546.119 I slot print_timing: id 2 | task 7956 | n_decoded = 240, tg = 15.40 t/s, tg_3s = 15.12 t/s
94.55.601.447 I slot print_timing: id 2 | task 7956 | n_decoded = 287, tg = 15.40 t/s, tg_3s = 15.38 t/s
94.58.661.765 I slot print_timing: id 2 | task 7956 | n_decoded = 333, tg = 15.34 t/s, tg_3s = 15.03 t/s
95.01.711.495 I slot print_timing: id 2 | task 7956 | n_decoded = 379, tg = 15.31 t/s, tg_3s = 15.08 t/s
95.04.757.351 I slot print_timing: id 2 | task 7956 | n_decoded = 426, tg = 15.33 t/s, tg_3s = 15.43 t/s
95.07.797.665 I slot print_timing: id 2 | task 7956 | n_decoded = 473, tg = 15.34 t/s, tg_3s = 15.46 t/s
95.10.856.555 I slot print_timing: id 2 | task 7956 | n_decoded = 520, tg = 15.34 t/s, tg_3s = 15.37 t/s
95.13.912.305 I slot print_timing: id 2 | task 7956 | n_decoded = 567, tg = 15.34 t/s, tg_3s = 15.38 t/s
95.16.953.428 I slot print_timing: id 2 | task 7956 | prompt eval time = 804519.35 ms / 183475 tokens ( 4.38 ms per token, 228.06 tokens per second)
95.16.953.432 I slot print_timing: id 2 | task 7956 | eval time = 39993.09 ms / 613 tokens ( 65.24 ms per token, 15.33 tokens per second)
95.16.953.434 I slot print_timing: id 2 | task 7956 | total time = 844512.44 ms / 184088 tokens
95.16.953.435 I slot print_timing: id 2 | task 7956 | graphs reused = 8317
95.16.962.799 I slot release: id 2 | task 7956 | stop processing: n_tokens = 184087, truncated = 0
95.18.633.812 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 0.998
95.18.642.370 I slot launch_slot_: id 2 | task 8594 | processing task, is_child = 0
95.31.811.387 I slot print_timing: id 2 | task 8594 | prompt processing, n_tokens = 801, progress = 1.00, t = 13.17 s / 60.83 tokens per second
95.37.286.953 I slot print_timing: id 2 | task 8594 | prompt eval time = 13416.50 ms / 805 tokens ( 16.67 ms per token, 60.00 tokens per second)
95.37.286.959 I slot print_timing: id 2 | task 8594 | eval time = 5226.03 ms / 80 tokens ( 65.33 ms per token, 15.31 tokens per second)
95.37.286.961 I slot print_timing: id 2 | task 8594 | total time = 18642.53 ms / 885 tokens
95.37.286.979 I slot print_timing: id 2 | task 8594 | graphs reused = 8394
95.37.296.003 I slot release: id 2 | task 8594 | stop processing: n_tokens = 184355, truncated = 0
95.38.422.353 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 1.000
95.38.431.579 I slot launch_slot_: id 2 | task 8676 | processing task, is_child = 0
95.43.974.908 I slot print_timing: id 2 | task 8676 | prompt processing, n_tokens = 104, progress = 1.00, t = 5.54 s / 18.77 tokens per second
95.50.688.773 I slot print_timing: id 2 | task 8676 | n_decoded = 100, tg = 15.45 t/s, tg_3s = 15.45 t/s
95.53.720.506 I slot print_timing: id 2 | task 8676 | n_decoded = 146, tg = 15.36 t/s, tg_3s = 15.17 t/s
95.56.748.338 I slot print_timing: id 2 | task 8676 | n_decoded = 191, tg = 15.24 t/s, tg_3s = 14.86 t/s
95.59.789.817 I slot print_timing: id 2 | task 8676 | n_decoded = 238, tg = 15.28 t/s, tg_3s = 15.45 t/s
96.02.795.639 I slot print_timing: id 2 | task 8676 | n_decoded = 284, tg = 15.29 t/s, tg_3s = 15.30 t/s
96.04.969.146 I slot print_timing: id 2 | task 8676 | prompt eval time = 5784.50 ms / 108 tokens ( 53.56 ms per token, 18.67 tokens per second)
96.04.969.152 I slot print_timing: id 2 | task 8676 | eval time = 20751.36 ms / 317 tokens ( 65.46 ms per token, 15.28 tokens per second)
96.04.969.153 I slot print_timing: id 2 | task 8676 | total time = 26535.86 ms / 425 tokens
96.04.969.155 I slot print_timing: id 2 | task 8676 | graphs reused = 8708
96.04.977.356 I slot release: id 2 | task 8676 | stop processing: n_tokens = 184696, truncated = 0
96.06.381.282 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.981 (> 0.100 thold), f_keep = 0.999
96.06.390.365 I slot launch_slot_: id 2 | task 8995 | processing task, is_child = 0
96.35.691.150 I slot print_timing: id 2 | task 8995 | prompt processing, n_tokens = 3628, progress = 1.00, t = 29.30 s / 123.83 tokens per second
96.42.425.466 I slot print_timing: id 2 | task 8995 | n_decoded = 100, tg = 15.42 t/s, tg_3s = 15.42 t/s
96.45.433.540 I slot print_timing: id 2 | task 8995 | n_decoded = 146, tg = 15.38 t/s, tg_3s = 15.29 t/s
96.48.460.267 I slot print_timing: id 2 | task 8995 | n_decoded = 192, tg = 15.33 t/s, tg_3s = 15.20 t/s
96.51.479.692 I slot print_timing: id 2 | task 8995 | n_decoded = 238, tg = 15.32 t/s, tg_3s = 15.23 t/s
96.54.494.171 I slot print_timing: id 2 | task 8995 | n_decoded = 284, tg = 15.31 t/s, tg_3s = 15.26 t/s
96.57.551.903 I slot print_timing: id 2 | task 8995 | n_decoded = 331, tg = 15.32 t/s, tg_3s = 15.37 t/s
97.00.599.964 I slot print_timing: id 2 | task 8995 | n_decoded = 378, tg = 15.33 t/s, tg_3s = 15.42 t/s
97.03.650.319 I slot print_timing: id 2 | task 8995 | n_decoded = 425, tg = 15.34 t/s, tg_3s = 15.41 t/s
97.06.706.677 I slot print_timing: id 2 | task 8995 | n_decoded = 472, tg = 15.34 t/s, tg_3s = 15.38 t/s
97.09.753.110 I slot print_timing: id 2 | task 8995 | n_decoded = 519, tg = 15.35 t/s, tg_3s = 15.43 t/s
97.12.800.999 I slot print_timing: id 2 | task 8995 | n_decoded = 566, tg = 15.35 t/s, tg_3s = 15.42 t/s
97.15.844.072 I slot print_timing: id 2 | task 8995 | n_decoded = 613, tg = 15.36 t/s, tg_3s = 15.44 t/s
97.18.853.642 I slot print_timing: id 2 | task 8995 | n_decoded = 659, tg = 15.36 t/s, tg_3s = 15.28 t/s
97.21.859.375 I slot print_timing: id 2 | task 8995 | n_decoded = 705, tg = 15.35 t/s, tg_3s = 15.30 t/s
97.24.900.570 I slot print_timing: id 2 | task 8995 | n_decoded = 752, tg = 15.36 t/s, tg_3s = 15.45 t/s
97.27.959.364 I slot print_timing: id 2 | task 8995 | n_decoded = 799, tg = 15.36 t/s, tg_3s = 15.37 t/s
97.31.005.584 I slot print_timing: id 2 | task 8995 | n_decoded = 846, tg = 15.36 t/s, tg_3s = 15.43 t/s
97.34.055.480 I slot print_timing: id 2 | task 8995 | n_decoded = 893, tg = 15.37 t/s, tg_3s = 15.41 t/s
97.37.104.817 I slot print_timing: id 2 | task 8995 | n_decoded = 940, tg = 15.37 t/s, tg_3s = 15.41 t/s
97.40.152.093 I slot print_timing: id 2 | task 8995 | n_decoded = 987, tg = 15.37 t/s, tg_3s = 15.42 t/s
97.43.201.267 I slot print_timing: id 2 | task 8995 | n_decoded = 1034, tg = 15.37 t/s, tg_3s = 15.41 t/s
97.46.235.340 I slot print_timing: id 2 | task 8995 | n_decoded = 1081, tg = 15.38 t/s, tg_3s = 15.49 t/s
97.49.278.294 I slot print_timing: id 2 | task 8995 | n_decoded = 1128, tg = 15.38 t/s, tg_3s = 15.45 t/s
97.52.322.015 I slot print_timing: id 2 | task 8995 | n_decoded = 1175, tg = 15.38 t/s, tg_3s = 15.44 t/s
97.55.324.849 I slot print_timing: id 2 | task 8995 | n_decoded = 1221, tg = 15.38 t/s, tg_3s = 15.32 t/s
97.58.378.919 I slot print_timing: id 2 | task 8995 | n_decoded = 1268, tg = 15.38 t/s, tg_3s = 15.39 t/s
98.01.443.291 I slot print_timing: id 2 | task 8995 | n_decoded = 1315, tg = 15.38 t/s, tg_3s = 15.34 t/s
98.04.459.128 I slot print_timing: id 2 | task 8995 | n_decoded = 1360, tg = 15.36 t/s, tg_3s = 14.92 t/s
98.07.521.258 I slot print_timing: id 2 | task 8995 | n_decoded = 1407, tg = 15.36 t/s, tg_3s = 15.35 t/s
98.10.524.306 I slot print_timing: id 2 | task 8995 | n_decoded = 1453, tg = 15.36 t/s, tg_3s = 15.32 t/s
98.13.535.759 I slot print_timing: id 2 | task 8995 | n_decoded = 1499, tg = 15.36 t/s, tg_3s = 15.28 t/s
98.16.536.500 I slot print_timing: id 2 | task 8995 | n_decoded = 1545, tg = 15.36 t/s, tg_3s = 15.33 t/s
98.19.550.034 I slot print_timing: id 2 | task 8995 | n_decoded = 1591, tg = 15.36 t/s, tg_3s = 15.26 t/s
98.22.594.876 I slot print_timing: id 2 | task 8995 | n_decoded = 1637, tg = 15.35 t/s, tg_3s = 15.11 t/s
98.25.597.184 I slot print_timing: id 2 | task 8995 | n_decoded = 1683, tg = 15.35 t/s, tg_3s = 15.32 t/s
98.28.628.802 I slot print_timing: id 2 | task 8995 | n_decoded = 1730, tg = 15.35 t/s, tg_3s = 15.50 t/s
98.31.632.700 I slot print_timing: id 2 | task 8995 | n_decoded = 1777, tg = 15.36 t/s, tg_3s = 15.65 t/s
98.34.643.553 I slot print_timing: id 2 | task 8995 | n_decoded = 1824, tg = 15.37 t/s, tg_3s = 15.61 t/s
98.37.663.639 I slot print_timing: id 2 | task 8995 | n_decoded = 1871, tg = 15.37 t/s, tg_3s = 15.56 t/s
98.40.709.090 I slot print_timing: id 2 | task 8995 | n_decoded = 1918, tg = 15.37 t/s, tg_3s = 15.43 t/s
98.43.764.853 I slot print_timing: id 2 | task 8995 | n_decoded = 1965, tg = 15.37 t/s, tg_3s = 15.38 t/s
98.46.813.831 I slot print_timing: id 2 | task 8995 | n_decoded = 2012, tg = 15.37 t/s, tg_3s = 15.41 t/s
98.49.823.755 I slot print_timing: id 2 | task 8995 | n_decoded = 2059, tg = 15.38 t/s, tg_3s = 15.62 t/s
98.52.835.454 I slot print_timing: id 2 | task 8995 | n_decoded = 2106, tg = 15.38 t/s, tg_3s = 15.61 t/s
98.55.837.002 I slot print_timing: id 2 | task 8995 | n_decoded = 2153, tg = 15.39 t/s, tg_3s = 15.66 t/s
98.58.837.305 I slot print_timing: id 2 | task 8995 | n_decoded = 2200, tg = 15.40 t/s, tg_3s = 15.66 t/s
99.01.855.822 I slot print_timing: id 2 | task 8995 | n_decoded = 2247, tg = 15.40 t/s, tg_3s = 15.57 t/s
99.04.877.493 I slot print_timing: id 2 | task 8995 | n_decoded = 2294, tg = 15.40 t/s, tg_3s = 15.55 t/s
99.07.907.714 I slot print_timing: id 2 | task 8995 | n_decoded = 2341, tg = 15.40 t/s, tg_3s = 15.51 t/s
99.10.942.264 I slot print_timing: id 2 | task 8995 | n_decoded = 2388, tg = 15.41 t/s, tg_3s = 15.49 t/s
99.13.986.889 I slot print_timing: id 2 | task 8995 | n_decoded = 2435, tg = 15.41 t/s, tg_3s = 15.44 t/s
99.17.042.735 I slot print_timing: id 2 | task 8995 | n_decoded = 2482, tg = 15.41 t/s, tg_3s = 15.38 t/s
99.20.086.025 I slot print_timing: id 2 | task 8995 | n_decoded = 2528, tg = 15.40 t/s, tg_3s = 15.12 t/s
99.23.099.765 I slot print_timing: id 2 | task 8995 | n_decoded = 2575, tg = 15.40 t/s, tg_3s = 15.60 t/s
99.26.143.928 I slot print_timing: id 2 | task 8995 | n_decoded = 2622, tg = 15.41 t/s, tg_3s = 15.44 t/s
99.29.192.510 I slot print_timing: id 2 | task 8995 | n_decoded = 2669, tg = 15.41 t/s, tg_3s = 15.42 t/s
99.32.226.010 I slot print_timing: id 2 | task 8995 | n_decoded = 2716, tg = 15.41 t/s, tg_3s = 15.49 t/s
99.35.228.277 I slot print_timing: id 2 | task 8995 | n_decoded = 2762, tg = 15.41 t/s, tg_3s = 15.32 t/s
99.35.357.779 I slot print_timing: id 2 | task 8995 | prompt eval time = 29547.53 ms / 3632 tokens ( 8.14 ms per token, 122.92 tokens per second)
99.35.357.783 I slot print_timing: id 2 | task 8995 | eval time = 179417.97 ms / 2764 tokens ( 64.91 ms per token, 15.41 tokens per second)
99.35.357.785 I slot print_timing: id 2 | task 8995 | total time = 208965.50 ms / 6396 tokens
99.35.357.786 I slot print_timing: id 2 | task 8995 | graphs reused = 11459
99.35.365.764 I slot release: id 2 | task 8995 | stop processing: n_tokens = 190771, truncated = 0
99.36.851.374 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.991 (> 0.100 thold), f_keep = 0.993
99.36.859.819 I slot launch_slot_: id 2 | task 11761 | processing task, is_child = 0
100.03.359.326 I slot print_timing: id 2 | task 11761 | prompt processing, n_tokens = 3061, progress = 1.00, t = 26.50 s / 115.52 tokens per second
100.10.088.516 I slot print_timing: id 2 | task 11761 | n_decoded = 100, tg = 15.42 t/s, tg_3s = 15.42 t/s
100.11.213.643 I slot print_timing: id 2 | task 11761 | prompt eval time = 26739.87 ms / 3065 tokens ( 8.72 ms per token, 114.62 tokens per second)
100.11.213.647 I slot print_timing: id 2 | task 11761 | eval time = 7611.93 ms / 117 tokens ( 65.06 ms per token, 15.37 tokens per second)
100.11.213.649 I slot print_timing: id 2 | task 11761 | total time = 34351.80 ms / 3182 tokens
100.11.213.651 I slot print_timing: id 2 | task 11761 | graphs reused = 11574
100.11.222.021 I slot release: id 2 | task 11761 | stop processing: n_tokens = 191185, truncated = 0
100.12.410.609 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.994 (> 0.100 thold), f_keep = 1.000
100.12.418.749 I slot launch_slot_: id 2 | task 11880 | processing task, is_child = 0
100.28.513.254 I slot print_timing: id 2 | task 11880 | prompt processing, n_tokens = 1283, progress = 1.00, t = 16.09 s / 79.73 tokens per second
100.35.281.896 I slot print_timing: id 2 | task 11880 | n_decoded = 100, tg = 15.33 t/s, tg_3s = 15.33 t/s
100.38.333.130 I slot print_timing: id 2 | task 11880 | n_decoded = 147, tg = 15.35 t/s, tg_3s = 15.40 t/s
100.41.335.280 I slot print_timing: id 2 | task 11880 | n_decoded = 193, tg = 15.34 t/s, tg_3s = 15.32 t/s
100.42.847.550 I slot print_timing: id 2 | task 11880 | prompt eval time = 16336.07 ms / 1287 tokens ( 12.69 ms per token, 78.78 tokens per second)
100.42.847.554 I slot print_timing: id 2 | task 11880 | eval time = 14090.79 ms / 216 tokens ( 65.24 ms per token, 15.33 tokens per second)
100.42.847.556 I slot print_timing: id 2 | task 11880 | total time = 30426.86 ms / 1503 tokens
100.42.847.557 I slot print_timing: id 2 | task 11880 | graphs reused = 11787
100.42.856.168 I slot release: id 2 | task 11880 | stop processing: n_tokens = 192567, truncated = 0
100.44.157.683 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
100.44.166.053 I slot launch_slot_: id 2 | task 12098 | processing task, is_child = 0
100.55.734.808 I slot print_timing: id 2 | task 12098 | prompt processing, n_tokens = 502, progress = 1.00, t = 11.57 s / 43.40 tokens per second
101.02.517.867 I slot print_timing: id 2 | task 12098 | n_decoded = 100, tg = 15.32 t/s, tg_3s = 15.32 t/s
101.04.807.720 I slot print_timing: id 2 | task 12098 | prompt eval time = 11820.81 ms / 506 tokens ( 23.36 ms per token, 42.81 tokens per second)
101.04.807.724 I slot print_timing: id 2 | task 12098 | eval time = 8818.92 ms / 134 tokens ( 65.81 ms per token, 15.19 tokens per second)
101.04.807.726 I slot print_timing: id 2 | task 12098 | total time = 20639.73 ms / 640 tokens
101.04.807.727 I slot print_timing: id 2 | task 12098 | graphs reused = 11919
101.04.816.207 I slot release: id 2 | task 12098 | stop processing: n_tokens = 192987, truncated = 0
101.05.974.235 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 1.000
101.05.983.110 I slot launch_slot_: id 2 | task 12234 | processing task, is_child = 0
101.12.914.130 I slot print_timing: id 2 | task 12234 | prompt processing, n_tokens = 169, progress = 1.00, t = 6.93 s / 24.39 tokens per second
101.19.596.223 I slot print_timing: id 2 | task 12234 | n_decoded = 100, tg = 15.53 t/s, tg_3s = 15.53 t/s
101.22.641.962 I slot print_timing: id 2 | task 12234 | n_decoded = 146, tg = 15.39 t/s, tg_3s = 15.10 t/s
101.25.691.753 I slot print_timing: id 2 | task 12234 | n_decoded = 193, tg = 15.40 t/s, tg_3s = 15.41 t/s
101.28.747.072 I slot print_timing: id 2 | task 12234 | n_decoded = 240, tg = 15.39 t/s, tg_3s = 15.38 t/s
101.31.797.672 I slot print_timing: id 2 | task 12234 | n_decoded = 287, tg = 15.40 t/s, tg_3s = 15.41 t/s
101.34.839.215 I slot print_timing: id 2 | task 12234 | n_decoded = 334, tg = 15.40 t/s, tg_3s = 15.45 t/s
101.36.628.420 I slot print_timing: id 2 | task 12234 | prompt eval time = 7170.63 ms / 173 tokens ( 41.45 ms per token, 24.13 tokens per second)
101.36.628.424 I slot print_timing: id 2 | task 12234 | eval time = 23472.91 ms / 361 tokens ( 65.02 ms per token, 15.38 tokens per second)
101.36.628.426 I slot print_timing: id 2 | task 12234 | total time = 30643.54 ms / 534 tokens
101.36.628.427 I slot print_timing: id 2 | task 12234 | graphs reused = 12276
101.36.637.021 I slot release: id 2 | task 12234 | stop processing: n_tokens = 193383, truncated = 0
101.37.906.982 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
101.37.915.660 I slot launch_slot_: id 2 | task 12597 | processing task, is_child = 0
101.48.647.874 I slot print_timing: id 2 | task 12597 | prompt processing, n_tokens = 431, progress = 1.00, t = 10.73 s / 40.17 tokens per second
101.55.403.393 I slot print_timing: id 2 | task 12597 | n_decoded = 100, tg = 15.37 t/s, tg_3s = 15.37 t/s
101.58.414.956 I slot print_timing: id 2 | task 12597 | n_decoded = 146, tg = 15.34 t/s, tg_3s = 15.27 t/s
102.01.427.917 I slot print_timing: id 2 | task 12597 | n_decoded = 192, tg = 15.32 t/s, tg_3s = 15.27 t/s
102.04.437.741 I slot print_timing: id 2 | task 12597 | n_decoded = 237, tg = 15.25 t/s, tg_3s = 14.95 t/s
102.05.377.590 I slot print_timing: id 2 | task 12597 | prompt eval time = 10980.51 ms / 435 tokens ( 25.24 ms per token, 39.62 tokens per second)
102.05.377.594 I slot print_timing: id 2 | task 12597 | eval time = 16479.33 ms / 251 tokens ( 65.65 ms per token, 15.23 tokens per second)
102.05.377.596 I slot print_timing: id 2 | task 12597 | total time = 27459.85 ms / 686 tokens
102.05.377.597 I slot print_timing: id 2 | task 12597 | graphs reused = 12524
102.05.386.271 I slot release: id 2 | task 12597 | stop processing: n_tokens = 193704, truncated = 0
102.06.669.192 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.996 (> 0.100 thold), f_keep = 1.000
102.06.677.709 I slot launch_slot_: id 2 | task 12850 | processing task, is_child = 0
102.21.349.150 I slot print_timing: id 2 | task 12850 | prompt processing, n_tokens = 970, progress = 1.00, t = 14.67 s / 66.12 tokens per second
102.28.114.116 I slot print_timing: id 2 | task 12850 | n_decoded = 100, tg = 15.36 t/s, tg_3s = 15.36 t/s
102.31.161.514 I slot print_timing: id 2 | task 12850 | n_decoded = 147, tg = 15.38 t/s, tg_3s = 15.42 t/s
102.34.204.599 I slot print_timing: id 2 | task 12850 | n_decoded = 194, tg = 15.40 t/s, tg_3s = 15.44 t/s
102.37.211.140 I slot print_timing: id 2 | task 12850 | n_decoded = 240, tg = 15.38 t/s, tg_3s = 15.30 t/s
102.40.269.740 I slot print_timing: id 2 | task 12850 | n_decoded = 287, tg = 15.38 t/s, tg_3s = 15.37 t/s
102.43.278.741 I slot print_timing: id 2 | task 12850 | n_decoded = 332, tg = 15.32 t/s, tg_3s = 14.96 t/s
102.46.333.100 I slot print_timing: id 2 | task 12850 | n_decoded = 379, tg = 15.33 t/s, tg_3s = 15.39 t/s
102.49.337.698 I slot print_timing: id 2 | task 12850 | n_decoded = 425, tg = 15.32 t/s, tg_3s = 15.31 t/s
102.52.400.875 I slot print_timing: id 2 | task 12850 | n_decoded = 472, tg = 15.33 t/s, tg_3s = 15.34 t/s
102.55.459.081 I slot print_timing: id 2 | task 12850 | n_decoded = 519, tg = 15.33 t/s, tg_3s = 15.37 t/s
102.58.506.601 I slot print_timing: id 2 | task 12850 | n_decoded = 566, tg = 15.34 t/s, tg_3s = 15.42 t/s
103.01.539.125 I slot print_timing: id 2 | task 12850 | n_decoded = 613, tg = 15.35 t/s, tg_3s = 15.50 t/s
103.04.539.705 I slot print_timing: id 2 | task 12850 | n_decoded = 659, tg = 15.35 t/s, tg_3s = 15.33 t/s
103.07.583.967 I slot print_timing: id 2 | task 12850 | n_decoded = 706, tg = 15.35 t/s, tg_3s = 15.44 t/s
103.10.630.518 I slot print_timing: id 2 | task 12850 | n_decoded = 753, tg = 15.36 t/s, tg_3s = 15.43 t/s
103.13.642.620 I slot print_timing: id 2 | task 12850 | n_decoded = 799, tg = 15.35 t/s, tg_3s = 15.27 t/s
103.13.902.957 I slot print_timing: id 2 | task 12850 | prompt eval time = 14924.56 ms / 974 tokens ( 15.32 ms per token, 65.26 tokens per second)
103.13.902.962 I slot print_timing: id 2 | task 12850 | eval time = 52298.71 ms / 803 tokens ( 65.13 ms per token, 15.35 tokens per second)
103.13.902.963 I slot print_timing: id 2 | task 12850 | total time = 67223.27 ms / 1777 tokens
103.13.902.965 I slot print_timing: id 2 | task 12850 | graphs reused = 13322
103.13.911.898 I slot release: id 2 | task 12850 | stop processing: n_tokens = 195226, truncated = 0
103.15.448.731 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.996 (> 0.100 thold), f_keep = 0.996
103.15.457.323 I slot launch_slot_: id 2 | task 13655 | processing task, is_child = 0
103.29.533.217 I slot print_timing: id 2 | task 13655 | prompt processing, n_tokens = 925, progress = 1.00, t = 14.07 s / 65.72 tokens per second
103.36.273.286 I slot print_timing: id 2 | task 13655 | n_decoded = 100, tg = 15.42 t/s, tg_3s = 15.42 t/s
103.39.333.189 I slot print_timing: id 2 | task 13655 | n_decoded = 147, tg = 15.40 t/s, tg_3s = 15.36 t/s
103.42.383.030 I slot print_timing: id 2 | task 13655 | n_decoded = 194, tg = 15.40 t/s, tg_3s = 15.41 t/s
103.45.445.714 I slot print_timing: id 2 | task 13655 | n_decoded = 241, tg = 15.39 t/s, tg_3s = 15.35 t/s
103.48.449.019 I slot print_timing: id 2 | task 13655 | n_decoded = 287, tg = 15.38 t/s, tg_3s = 15.32 t/s
103.51.497.545 I slot print_timing: id 2 | task 13655 | n_decoded = 334, tg = 15.38 t/s, tg_3s = 15.42 t/s
103.54.541.526 I slot print_timing: id 2 | task 13655 | n_decoded = 381, tg = 15.39 t/s, tg_3s = 15.44 t/s
103.55.339.010 I slot print_timing: id 2 | task 13655 | prompt eval time = 14328.62 ms / 929 tokens ( 15.42 ms per token, 64.84 tokens per second)
103.55.339.014 I slot print_timing: id 2 | task 13655 | eval time = 25550.96 ms / 393 tokens ( 65.02 ms per token, 15.38 tokens per second)
103.55.339.016 I slot print_timing: id 2 | task 13655 | total time = 39879.58 ms / 1322 tokens
103.55.339.017 I slot print_timing: id 2 | task 13655 | graphs reused = 13712
103.55.347.679 I slot release: id 2 | task 13655 | stop processing: n_tokens = 195741, truncated = 0
103.56.500.366 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 0.998
103.56.508.497 I slot launch_slot_: id 2 | task 14050 | processing task, is_child = 0
104.08.858.944 I slot print_timing: id 2 | task 14050 | prompt processing, n_tokens = 646, progress = 1.00, t = 12.35 s / 52.31 tokens per second
104.13.505.432 I slot print_timing: id 2 | task 14050 | prompt eval time = 12587.70 ms / 650 tokens ( 19.37 ms per token, 51.64 tokens per second)
104.13.505.439 I slot print_timing: id 2 | task 14050 | eval time = 4407.31 ms / 68 tokens ( 64.81 ms per token, 15.43 tokens per second)
104.13.505.441 I slot print_timing: id 2 | task 14050 | total time = 16995.01 ms / 718 tokens
104.13.505.443 I slot print_timing: id 2 | task 14050 | graphs reused = 13778
104.13.514.111 I slot release: id 2 | task 14050 | stop processing: n_tokens = 196062, truncated = 0
104.14.775.976 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.996 (> 0.100 thold), f_keep = 1.000
104.14.784.448 I slot launch_slot_: id 2 | task 14120 | processing task, is_child = 0
104.28.072.630 I slot print_timing: id 2 | task 14120 | prompt processing, n_tokens = 809, progress = 1.00, t = 13.29 s / 60.89 tokens per second
104.34.861.478 I slot print_timing: id 2 | task 14120 | n_decoded = 100, tg = 15.30 t/s, tg_3s = 15.30 t/s
104.37.862.547 I slot print_timing: id 2 | task 14120 | n_decoded = 146, tg = 15.31 t/s, tg_3s = 15.33 t/s
104.40.920.111 I slot print_timing: id 2 | task 14120 | n_decoded = 193, tg = 15.32 t/s, tg_3s = 15.37 t/s
104.43.929.042 I slot print_timing: id 2 | task 14120 | n_decoded = 239, tg = 15.32 t/s, tg_3s = 15.29 t/s
104.46.999.001 I slot print_timing: id 2 | task 14120 | n_decoded = 286, tg = 15.32 t/s, tg_3s = 15.31 t/s
104.50.003.050 I slot print_timing: id 2 | task 14120 | n_decoded = 332, tg = 15.32 t/s, tg_3s = 15.31 t/s
104.50.872.616 I slot print_timing: id 2 | task 14120 | prompt eval time = 13538.69 ms / 813 tokens ( 16.65 ms per token, 60.05 tokens per second)
104.50.872.624 I slot print_timing: id 2 | task 14120 | eval time = 22547.52 ms / 345 tokens ( 65.36 ms per token, 15.30 tokens per second)
104.50.872.626 I slot print_timing: id 2 | task 14120 | total time = 36086.21 ms / 1158 tokens
104.50.872.628 I slot print_timing: id 2 | task 14120 | graphs reused = 14119
104.50.881.375 I slot release: id 2 | task 14120 | stop processing: n_tokens = 197148, truncated = 0
104.52.172.759 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 0.998
104.52.181.267 I slot launch_slot_: id 2 | task 14467 | processing task, is_child = 0
105.04.555.335 I slot print_timing: id 2 | task 14467 | prompt processing, n_tokens = 635, progress = 1.00, t = 12.37 s / 51.32 tokens per second
105.11.279.006 I slot print_timing: id 2 | task 14467 | n_decoded = 100, tg = 15.45 t/s, tg_3s = 15.45 t/s
105.14.328.100 I slot print_timing: id 2 | task 14467 | n_decoded = 147, tg = 15.44 t/s, tg_3s = 15.41 t/s
105.17.356.033 I slot print_timing: id 2 | task 14467 | n_decoded = 192, tg = 15.30 t/s, tg_3s = 14.86 t/s
105.20.399.789 I slot print_timing: id 2 | task 14467 | n_decoded = 238, tg = 15.26 t/s, tg_3s = 15.11 t/s
105.23.409.824 I slot print_timing: id 2 | task 14467 | n_decoded = 284, tg = 15.27 t/s, tg_3s = 15.28 t/s
105.24.714.895 I slot print_timing: id 2 | task 14467 | prompt eval time = 12624.10 ms / 639 tokens ( 19.76 ms per token, 50.62 tokens per second)
105.24.714.900 I slot print_timing: id 2 | task 14467 | eval time = 19907.64 ms / 304 tokens ( 65.49 ms per token, 15.27 tokens per second)
105.24.714.902 I slot print_timing: id 2 | task 14467 | total time = 32531.75 ms / 943 tokens
105.24.714.903 I slot print_timing: id 2 | task 14467 | graphs reused = 14420
105.24.723.888 I slot release: id 2 | task 14467 | stop processing: n_tokens = 197742, truncated = 0
105.26.004.202 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.999
105.26.012.811 I slot launch_slot_: id 2 | task 14773 | processing task, is_child = 0
105.35.385.608 I slot print_timing: id 2 | task 14773 | prompt processing, n_tokens = 353, progress = 1.00, t = 9.37 s / 37.67 tokens per second
105.42.114.074 I slot print_timing: id 2 | task 14773 | n_decoded = 100, tg = 15.42 t/s, tg_3s = 15.42 t/s
105.45.128.861 I slot print_timing: id 2 | task 14773 | n_decoded = 146, tg = 15.37 t/s, tg_3s = 15.26 t/s
105.48.156.991 I slot print_timing: id 2 | task 14773 | n_decoded = 192, tg = 15.33 t/s, tg_3s = 15.19 t/s
105.51.214.052 I slot print_timing: id 2 | task 14773 | n_decoded = 239, tg = 15.34 t/s, tg_3s = 15.37 t/s
105.54.215.224 I slot print_timing: id 2 | task 14773 | n_decoded = 285, tg = 15.34 t/s, tg_3s = 15.33 t/s
105.57.224.850 I slot print_timing: id 2 | task 14773 | n_decoded = 331, tg = 15.33 t/s, tg_3s = 15.28 t/s
106.00.237.501 I slot print_timing: id 2 | task 14773 | n_decoded = 377, tg = 15.32 t/s, tg_3s = 15.27 t/s
106.02.024.850 I slot print_timing: id 2 | task 14773 | prompt eval time = 9615.69 ms / 357 tokens ( 26.93 ms per token, 37.13 tokens per second)
106.02.024.855 I slot print_timing: id 2 | task 14773 | eval time = 26394.29 ms / 403 tokens ( 65.49 ms per token, 15.27 tokens per second)
106.02.024.856 I slot print_timing: id 2 | task 14773 | total time = 36009.99 ms / 760 tokens
106.02.024.858 I slot print_timing: id 2 | task 14773 | graphs reused = 14819
106.02.033.338 I slot release: id 2 | task 14773 | stop processing: n_tokens = 198194, truncated = 0
106.03.195.148 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
106.03.203.994 I slot launch_slot_: id 2 | task 15178 | processing task, is_child = 0
106.14.912.536 I slot print_timing: id 2 | task 15178 | prompt processing, n_tokens = 533, progress = 1.00, t = 11.71 s / 45.53 tokens per second
106.19.969.801 I slot print_timing: id 2 | task 15178 | prompt eval time = 11955.94 ms / 537 tokens ( 22.26 ms per token, 44.91 tokens per second)
106.19.969.805 I slot print_timing: id 2 | task 15178 | eval time = 4807.89 ms / 73 tokens ( 65.86 ms per token, 15.18 tokens per second)
106.19.969.807 I slot print_timing: id 2 | task 15178 | total time = 16763.83 ms / 610 tokens
106.19.969.809 I slot print_timing: id 2 | task 15178 | graphs reused = 14890
106.19.978.445 I slot release: id 2 | task 15178 | stop processing: n_tokens = 198397, truncated = 0
106.21.284.226 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.994 (> 0.100 thold), f_keep = 1.000
106.21.292.697 I slot launch_slot_: id 2 | task 15253 | processing task, is_child = 0
106.37.801.446 I slot print_timing: id 2 | task 15253 | prompt processing, n_tokens = 1364, progress = 1.00, t = 16.51 s / 82.63 tokens per second
106.44.589.260 I slot print_timing: id 2 | task 15253 | n_decoded = 100, tg = 15.30 t/s, tg_3s = 15.30 t/s

{took some entires down due large n repation}

169.24.434.793 I slot print_timing: id 2 | task 15253 | n_decoded = 56384, tg = 14.97 t/s, tg_3s = 14.46 t/s
169.27.477.889 I slot print_timing: id 2 | task 15253 | n_decoded = 56428, tg = 14.97 t/s, tg_3s = 14.46 t/s
169.30.524.992 I slot print_timing: id 2 | task 15253 | n_decoded = 56472, tg = 14.97 t/s, tg_3s = 14.44 t/s
169.33.562.894 I slot print_timing: id 2 | task 15253 | n_decoded = 56515, tg = 14.97 t/s, tg_3s = 14.15 t/s
169.33.703.186 W srv stop: cancel task, id_task = 15253
169.33.770.112 I slot release: id 2 | task 15253 | stop processing: n_tokens = 256206, truncated = 0
169.41.429.864 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.993 (> 0.100 thold), f_keep = 0.774
169.41.438.548 I slot launch_slot_: id 2 | task 71774 | processing task, is_child = 0
169.46.575.510 I slot print_timing: id 2 | task 71774 | prompt processing, n_tokens = 78, progress = 0.99, t = 5.13 s / 15.19 tokens per second
170.02.433.717 I slot print_timing: id 2 | task 71774 | prompt processing, n_tokens = 1379, progress = 1.00, t = 20.99 s / 65.69 tokens per second
170.09.208.314 I slot print_timing: id 2 | task 71774 | n_decoded = 100, tg = 15.31 t/s, tg_3s = 15.31 t/s
170.12.253.131 I slot print_timing: id 2 | task 71774 | n_decoded = 146, tg = 15.25 t/s, tg_3s = 15.11 t/s
170.15.310.895 I slot print_timing: id 2 | task 71774 | n_decoded = 191, tg = 15.12 t/s, tg_3s = 14.72 t/s
170.18.350.641 I slot print_timing: id 2 | task 71774 | n_decoded = 237, tg = 15.12 t/s, tg_3s = 15.13 t/s
170.21.379.492 I slot print_timing: id 2 | task 71774 | n_decoded = 283, tg = 15.13 t/s, tg_3s = 15.19 t/s
170.24.436.395 I slot print_timing: id 2 | task 71774 | n_decoded = 329, tg = 15.12 t/s, tg_3s = 15.05 t/s
170.27.441.094 I slot print_timing: id 2 | task 71774 | n_decoded = 374, tg = 15.10 t/s, tg_3s = 14.98 t/s
170.30.487.486 I slot print_timing: id 2 | task 71774 | n_decoded = 420, tg = 15.10 t/s, tg_3s = 15.10 t/s
170.33.515.112 I slot print_timing: id 2 | task 71774 | n_decoded = 466, tg = 15.11 t/s, tg_3s = 15.19 t/s
170.36.543.169 I slot print_timing: id 2 | task 71774 | n_decoded = 512, tg = 15.12 t/s, tg_3s = 15.19 t/s
170.39.569.571 I slot print_timing: id 2 | task 71774 | n_decoded = 558, tg = 15.13 t/s, tg_3s = 15.20 t/s
170.42.600.319 I slot print_timing: id 2 | task 71774 | n_decoded = 604, tg = 15.13 t/s, tg_3s = 15.18 t/s
170.45.641.163 I slot print_timing: id 2 | task 71774 | n_decoded = 650, tg = 15.13 t/s, tg_3s = 15.13 t/s
170.48.698.861 I slot print_timing: id 2 | task 71774 | n_decoded = 696, tg = 15.12 t/s, tg_3s = 15.04 t/s
170.51.226.472 I slot print_timing: id 2 | task 71774 | prompt eval time = 21237.75 ms / 1383 tokens ( 15.36 ms per token, 65.12 tokens per second)
170.51.226.493 I slot print_timing: id 2 | task 71774 | eval time = 48547.84 ms / 734 tokens ( 66.14 ms per token, 15.12 tokens per second)
170.51.226.494 I slot print_timing: id 2 | task 71774 | total time = 69785.59 ms / 2117 tokens
170.51.226.496 I slot print_timing: id 2 | task 71774 | graphs reused = 71916
170.51.235.180 I slot release: id 2 | task 71774 | stop processing: n_tokens = 200437, truncated = 0
170.52.516.246 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 0.997
170.52.525.467 I slot launch_slot_: id 2 | task 72511 | processing task, is_child = 0
171.05.780.303 I slot print_timing: id 2 | task 72511 | prompt processing, n_tokens = 807, progress = 1.00, t = 13.25 s / 60.89 tokens per second
171.12.610.751 I slot print_timing: id 2 | task 72511 | n_decoded = 100, tg = 15.22 t/s, tg_3s = 15.22 t/s
171.15.632.816 I slot print_timing: id 2 | task 72511 | n_decoded = 146, tg = 15.22 t/s, tg_3s = 15.22 t/s
171.18.670.599 I slot print_timing: id 2 | task 72511 | n_decoded = 192, tg = 15.20 t/s, tg_3s = 15.14 t/s
171.21.688.928 I slot print_timing: id 2 | task 72511 | n_decoded = 237, tg = 15.14 t/s, tg_3s = 14.91 t/s
171.24.712.022 I slot print_timing: id 2 | task 72511 | n_decoded = 283, tg = 15.16 t/s, tg_3s = 15.22 t/s
171.27.736.282 I slot print_timing: id 2 | task 72511 | n_decoded = 329, tg = 15.16 t/s, tg_3s = 15.21 t/s
171.30.773.646 I slot print_timing: id 2 | task 72511 | n_decoded = 375, tg = 15.16 t/s, tg_3s = 15.14 t/s
171.33.794.613 I slot print_timing: id 2 | task 72511 | n_decoded = 421, tg = 15.17 t/s, tg_3s = 15.23 t/s
171.36.840.686 I slot print_timing: id 2 | task 72511 | n_decoded = 467, tg = 15.16 t/s, tg_3s = 15.10 t/s
171.39.860.429 I slot print_timing: id 2 | task 72511 | n_decoded = 513, tg = 15.17 t/s, tg_3s = 15.23 t/s
171.42.891.689 I slot print_timing: id 2 | task 72511 | n_decoded = 559, tg = 15.17 t/s, tg_3s = 15.18 t/s
171.45.922.308 I slot print_timing: id 2 | task 72511 | n_decoded = 605, tg = 15.17 t/s, tg_3s = 15.18 t/s
171.48.942.103 I slot print_timing: id 2 | task 72511 | n_decoded = 651, tg = 15.17 t/s, tg_3s = 15.23 t/s
171.51.966.005 I slot print_timing: id 2 | task 72511 | n_decoded = 697, tg = 15.18 t/s, tg_3s = 15.21 t/s
171.54.983.003 I slot print_timing: id 2 | task 72511 | n_decoded = 743, tg = 15.18 t/s, tg_3s = 15.25 t/s
171.58.019.511 I slot print_timing: id 2 | task 72511 | n_decoded = 789, tg = 15.18 t/s, tg_3s = 15.15 t/s
171.59.620.901 I slot print_timing: id 2 | task 72511 | prompt eval time = 13511.51 ms / 811 tokens ( 16.66 ms per token, 60.02 tokens per second)
171.59.620.906 I slot print_timing: id 2 | task 72511 | eval time = 53581.70 ms / 813 tokens ( 65.91 ms per token, 15.17 tokens per second)
171.59.620.907 I slot print_timing: id 2 | task 72511 | total time = 67093.21 ms / 1624 tokens
171.59.620.936 I slot print_timing: id 2 | task 72511 | graphs reused = 72724
171.59.629.508 I slot release: id 2 | task 72511 | stop processing: n_tokens = 201323, truncated = 0
172.01.076.549 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 0.997
172.01.085.411 I slot launch_slot_: id 2 | task 73326 | processing task, is_child = 0
172.15.175.242 I slot print_timing: id 2 | task 73326 | prompt processing, n_tokens = 887, progress = 1.00, t = 14.09 s / 62.96 tokens per second
172.22.040.724 I slot print_timing: id 2 | task 73326 | n_decoded = 100, tg = 15.10 t/s, tg_3s = 15.10 t/s
172.25.102.080 I slot print_timing: id 2 | task 73326 | n_decoded = 146, tg = 15.08 t/s, tg_3s = 15.03 t/s
172.27.295.595 I slot print_timing: id 2 | task 73326 | prompt eval time = 14331.61 ms / 891 tokens ( 16.08 ms per token, 62.17 tokens per second)
172.27.295.599 I slot print_timing: id 2 | task 73326 | eval time = 11876.30 ms / 178 tokens ( 66.72 ms per token, 14.99 tokens per second)
172.27.295.600 I slot print_timing: id 2 | task 73326 | total time = 26207.91 ms / 1069 tokens
172.27.295.602 I slot print_timing: id 2 | task 73326 | graphs reused = 72899
172.27.304.494 I slot release: id 2 | task 73326 | stop processing: n_tokens = 201575, truncated = 0
172.28.616.723 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.993 (> 0.100 thold), f_keep = 1.000
172.28.625.389 I slot launch_slot_: id 2 | task 73506 | processing task, is_child = 0
172.46.506.490 I slot print_timing: id 2 | task 73506 | prompt processing, n_tokens = 1533, progress = 1.00, t = 17.88 s / 85.74 tokens per second
172.53.391.516 I slot print_timing: id 2 | task 73506 | n_decoded = 100, tg = 15.07 t/s, tg_3s = 15.07 t/s
172.56.433.002 I slot print_timing: id 2 | task 73506 | n_decoded = 146, tg = 15.09 t/s, tg_3s = 15.12 t/s
172.59.483.996 I slot print_timing: id 2 | task 73506 | n_decoded = 192, tg = 15.09 t/s, tg_3s = 15.08 t/s
173.02.537.044 I slot print_timing: id 2 | task 73506 | n_decoded = 238, tg = 15.08 t/s, tg_3s = 15.07 t/s
173.05.577.897 I slot print_timing: id 2 | task 73506 | n_decoded = 284, tg = 15.09 t/s, tg_3s = 15.13 t/s
173.07.574.007 I slot print_timing: id 2 | task 73506 | prompt eval time = 18129.77 ms / 1537 tokens ( 11.80 ms per token, 84.78 tokens per second)
173.07.574.016 I slot print_timing: id 2 | task 73506 | eval time = 20816.75 ms / 314 tokens ( 66.30 ms per token, 15.08 tokens per second)
173.07.574.019 I slot print_timing: id 2 | task 73506 | total time = 38946.52 ms / 1851 tokens
173.07.574.021 I slot print_timing: id 2 | task 73506 | graphs reused = 73210
173.07.582.880 I slot release: id 2 | task 73506 | stop processing: n_tokens = 203244, truncated = 0
173.09.010.370 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 0.999
173.09.019.126 I slot launch_slot_: id 2 | task 73822 | processing task, is_child = 0
173.21.197.843 I slot print_timing: id 2 | task 73822 | prompt processing, n_tokens = 607, progress = 1.00, t = 12.18 s / 49.85 tokens per second
173.28.079.287 I slot print_timing: id 2 | task 73822 | n_decoded = 100, tg = 15.08 t/s, tg_3s = 15.08 t/s
173.31.086.327 I slot print_timing: id 2 | task 73822 | n_decoded = 146, tg = 15.15 t/s, tg_3s = 15.30 t/s
173.34.093.980 I slot print_timing: id 2 | task 73822 | n_decoded = 192, tg = 15.18 t/s, tg_3s = 15.29 t/s
173.37.100.139 I slot print_timing: id 2 | task 73822 | n_decoded = 238, tg = 15.20 t/s, tg_3s = 15.30 t/s
173.40.146.380 I slot print_timing: id 2 | task 73822 | n_decoded = 284, tg = 15.19 t/s, tg_3s = 15.10 t/s
173.42.200.111 I slot print_timing: id 2 | task 73822 | prompt eval time = 12426.00 ms / 611 tokens ( 20.34 ms per token, 49.17 tokens per second)
173.42.200.116 I slot print_timing: id 2 | task 73822 | eval time = 20753.11 ms / 315 tokens ( 65.88 ms per token, 15.18 tokens per second)
173.42.200.117 I slot print_timing: id 2 | task 73822 | total time = 33179.11 ms / 926 tokens
173.42.200.119 I slot print_timing: id 2 | task 73822 | graphs reused = 73522
173.42.209.141 I slot release: id 2 | task 73822 | stop processing: n_tokens = 203852, truncated = 0
173.43.705.379 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
173.43.714.117 I slot launch_slot_: id 2 | task 74139 | processing task, is_child = 0
173.53.581.648 I slot print_timing: id 2 | task 74139 | prompt processing, n_tokens = 388, progress = 1.00, t = 9.87 s / 39.33 tokens per second
174.00.422.302 I slot print_timing: id 2 | task 74139 | n_decoded = 100, tg = 15.18 t/s, tg_3s = 15.18 t/s
174.03.439.182 I slot print_timing: id 2 | task 74139 | n_decoded = 145, tg = 15.09 t/s, tg_3s = 14.92 t/s
174.06.463.702 I slot print_timing: id 2 | task 74139 | n_decoded = 191, tg = 15.12 t/s, tg_3s = 15.21 t/s
174.09.510.357 I slot print_timing: id 2 | task 74139 | n_decoded = 237, tg = 15.12 t/s, tg_3s = 15.10 t/s
174.12.517.519 I slot print_timing: id 2 | task 74139 | n_decoded = 282, tg = 15.09 t/s, tg_3s = 14.96 t/s
174.15.561.950 I slot print_timing: id 2 | task 74139 | n_decoded = 328, tg = 15.09 t/s, tg_3s = 15.11 t/s
174.17.496.583 I slot print_timing: id 2 | task 74139 | prompt eval time = 10116.58 ms / 392 tokens ( 25.81 ms per token, 38.75 tokens per second)
174.17.496.588 I slot print_timing: id 2 | task 74139 | eval time = 23663.88 ms / 356 tokens ( 66.47 ms per token, 15.04 tokens per second)
174.17.496.589 I slot print_timing: id 2 | task 74139 | total time = 33780.46 ms / 748 tokens
174.17.496.590 I slot print_timing: id 2 | task 74139 | graphs reused = 73875
174.17.505.503 I slot release: id 2 | task 74139 | stop processing: n_tokens = 204281, truncated = 0
174.18.870.334 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
174.18.878.752 I slot launch_slot_: id 2 | task 74497 | processing task, is_child = 0
174.29.141.830 I slot print_timing: id 2 | task 74497 | prompt processing, n_tokens = 426, progress = 1.00, t = 10.26 s / 41.52 tokens per second
174.36.029.608 I slot print_timing: id 2 | task 74497 | n_decoded = 100, tg = 15.09 t/s, tg_3s = 15.09 t/s
174.39.059.187 I slot print_timing: id 2 | task 74497 | n_decoded = 145, tg = 15.02 t/s, tg_3s = 14.85 t/s
174.42.100.092 I slot print_timing: id 2 | task 74497 | n_decoded = 191, tg = 15.04 t/s, tg_3s = 15.13 t/s
174.45.147.135 I slot print_timing: id 2 | task 74497 | n_decoded = 237, tg = 15.05 t/s, tg_3s = 15.10 t/s
174.48.199.552 I slot print_timing: id 2 | task 74497 | n_decoded = 283, tg = 15.06 t/s, tg_3s = 15.07 t/s
174.51.243.361 I slot print_timing: id 2 | task 74497 | n_decoded = 329, tg = 15.06 t/s, tg_3s = 15.11 t/s
174.54.289.285 I slot print_timing: id 2 | task 74497 | n_decoded = 375, tg = 15.07 t/s, tg_3s = 15.10 t/s
174.57.304.962 I slot print_timing: id 2 | task 74497 | n_decoded = 418, tg = 14.98 t/s, tg_3s = 14.26 t/s
175.00.344.297 I slot print_timing: id 2 | task 74497 | n_decoded = 464, tg = 15.00 t/s, tg_3s = 15.13 t/s
175.03.389.664 I slot print_timing: id 2 | task 74497 | n_decoded = 510, tg = 15.01 t/s, tg_3s = 15.10 t/s
175.06.422.989 I slot print_timing: id 2 | task 74497 | n_decoded = 556, tg = 15.02 t/s, tg_3s = 15.16 t/s
175.09.467.958 I slot print_timing: id 2 | task 74497 | n_decoded = 602, tg = 15.03 t/s, tg_3s = 15.11 t/s
175.12.515.230 I slot print_timing: id 2 | task 74497 | n_decoded = 648, tg = 15.03 t/s, tg_3s = 15.10 t/s
175.13.933.282 I slot print_timing: id 2 | task 74497 | prompt eval time = 10522.05 ms / 430 tokens ( 24.47 ms per token, 40.87 tokens per second)
175.13.933.287 I slot print_timing: id 2 | task 74497 | eval time = 44530.63 ms / 669 tokens ( 66.56 ms per token, 15.02 tokens per second)
175.13.933.288 I slot print_timing: id 2 | task 74497 | total time = 55052.69 ms / 1099 tokens
175.13.933.290 I slot print_timing: id 2 | task 74497 | graphs reused = 74540
175.13.942.069 I slot release: id 2 | task 74497 | stop processing: n_tokens = 205020, truncated = 0
175.15.516.631 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 0.997
175.15.525.788 I slot launch_slot_: id 2 | task 75168 | processing task, is_child = 0
175.29.087.803 I slot print_timing: id 2 | task 75168 | prompt processing, n_tokens = 790, progress = 1.00, t = 13.56 s / 58.26 tokens per second
175.35.944.610 I slot print_timing: id 2 | task 75168 | n_decoded = 100, tg = 15.14 t/s, tg_3s = 15.14 t/s
175.39.010.314 I slot print_timing: id 2 | task 75168 | n_decoded = 146, tg = 15.09 t/s, tg_3s = 15.00 t/s
175.42.050.395 I slot print_timing: id 2 | task 75168 | n_decoded = 192, tg = 15.10 t/s, tg_3s = 15.13 t/s
175.45.111.374 I slot print_timing: id 2 | task 75168 | n_decoded = 235, tg = 14.90 t/s, tg_3s = 14.05 t/s
175.48.151.640 I slot print_timing: id 2 | task 75168 | n_decoded = 281, tg = 14.94 t/s, tg_3s = 15.13 t/s
175.51.199.438 I slot print_timing: id 2 | task 75168 | n_decoded = 327, tg = 14.96 t/s, tg_3s = 15.09 t/s
175.54.211.162 I slot print_timing: id 2 | task 75168 | n_decoded = 373, tg = 15.00 t/s, tg_3s = 15.27 t/s
175.57.232.546 I slot print_timing: id 2 | task 75168 | n_decoded = 419, tg = 15.02 t/s, tg_3s = 15.22 t/s
176.00.251.005 I slot print_timing: id 2 | task 75168 | n_decoded = 465, tg = 15.04 t/s, tg_3s = 15.24 t/s
176.03.291.783 I slot print_timing: id 2 | task 75168 | n_decoded = 511, tg = 15.05 t/s, tg_3s = 15.13 t/s
176.06.317.601 I slot print_timing: id 2 | task 75168 | n_decoded = 557, tg = 15.06 t/s, tg_3s = 15.20 t/s
176.09.378.791 I slot print_timing: id 2 | task 75168 | n_decoded = 603, tg = 15.06 t/s, tg_3s = 15.03 t/s
176.10.193.130 I slot print_timing: id 2 | task 75168 | prompt eval time = 13810.38 ms / 794 tokens ( 17.39 ms per token, 57.49 tokens per second)
176.10.193.135 I slot print_timing: id 2 | task 75168 | eval time = 40854.89 ms / 615 tokens ( 66.43 ms per token, 15.05 tokens per second)
176.10.193.136 I slot print_timing: id 2 | task 75168 | total time = 54665.27 ms / 1409 tokens
176.10.193.137 I slot print_timing: id 2 | task 75168 | graphs reused = 75151
176.10.201.754 I slot release: id 2 | task 75168 | stop processing: n_tokens = 205756, truncated = 0
176.11.924.533 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.991 (> 0.100 thold), f_keep = 0.998
176.11.933.481 I slot launch_slot_: id 2 | task 75785 | processing task, is_child = 0
176.33.343.703 I slot print_timing: id 2 | task 75785 | prompt processing, n_tokens = 1964, progress = 1.00, t = 21.41 s / 91.74 tokens per second
176.40.288.518 I slot print_timing: id 2 | task 75785 | n_decoded = 100, tg = 14.94 t/s, tg_3s = 14.94 t/s
176.43.351.664 I slot print_timing: id 2 | task 75785 | n_decoded = 146, tg = 14.96 t/s, tg_3s = 15.02 t/s
176.46.368.525 I slot print_timing: id 2 | task 75785 | n_decoded = 190, tg = 14.87 t/s, tg_3s = 14.58 t/s
176.47.728.423 I slot print_timing: id 2 | task 75785 | prompt eval time = 21659.29 ms / 1968 tokens ( 11.01 ms per token, 90.86 tokens per second)
176.47.728.428 I slot print_timing: id 2 | task 75785 | eval time = 14133.50 ms / 210 tokens ( 67.30 ms per token, 14.86 tokens per second)
176.47.728.429 I slot print_timing: id 2 | task 75785 | total time = 35792.79 ms / 2178 tokens
176.47.728.431 I slot print_timing: id 2 | task 75785 | graphs reused = 75359
176.47.737.457 I slot release: id 2 | task 75785 | stop processing: n_tokens = 207315, truncated = 0
176.49.132.662 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 1.000
176.49.142.064 I slot launch_slot_: id 2 | task 75997 | processing task, is_child = 0
177.01.517.288 I slot print_timing: id 2 | task 75997 | prompt processing, n_tokens = 587, progress = 1.00, t = 12.37 s / 47.44 tokens per second
177.08.391.184 I slot print_timing: id 2 | task 75997 | n_decoded = 100, tg = 15.12 t/s, tg_3s = 15.12 t/s
177.11.453.710 I slot print_timing: id 2 | task 75997 | n_decoded = 146, tg = 15.09 t/s, tg_3s = 15.02 t/s
177.13.133.713 I slot print_timing: id 2 | task 75997 | prompt eval time = 12633.78 ms / 591 tokens ( 21.38 ms per token, 46.78 tokens per second)
177.13.133.718 I slot print_timing: id 2 | task 75997 | eval time = 11355.63 ms / 171 tokens ( 66.41 ms per token, 15.06 tokens per second)
177.13.133.719 I slot print_timing: id 2 | task 75997 | total time = 23989.41 ms / 762 tokens
177.13.133.721 I slot print_timing: id 2 | task 75997 | graphs reused = 75528
177.13.142.816 I slot release: id 2 | task 75997 | stop processing: n_tokens = 207863, truncated = 0
177.14.474.437 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 1.000
177.14.483.318 I slot launch_slot_: id 2 | task 76170 | processing task, is_child = 0
177.23.420.822 I slot print_timing: id 2 | task 76170 | prompt processing, n_tokens = 260, progress = 1.00, t = 8.94 s / 29.10 tokens per second
177.30.303.469 I slot print_timing: id 2 | task 76170 | n_decoded = 100, tg = 15.08 t/s, tg_3s = 15.08 t/s
177.33.309.834 I slot print_timing: id 2 | task 76170 | n_decoded = 145, tg = 15.05 t/s, tg_3s = 14.97 t/s
177.36.340.446 I slot print_timing: id 2 | task 76170 | n_decoded = 190, tg = 15.00 t/s, tg_3s = 14.85 t/s
177.39.355.375 I slot print_timing: id 2 | task 76170 | n_decoded = 235, tg = 14.99 t/s, tg_3s = 14.93 t/s
177.42.401.571 I slot print_timing: id 2 | task 76170 | n_decoded = 278, tg = 14.84 t/s, tg_3s = 14.12 t/s
177.45.458.330 I slot print_timing: id 2 | task 76170 | n_decoded = 323, tg = 14.83 t/s, tg_3s = 14.72 t/s
177.48.529.557 I slot print_timing: id 2 | task 76170 | n_decoded = 367, tg = 14.76 t/s, tg_3s = 14.33 t/s
177.51.533.316 I slot print_timing: id 2 | task 76170 | n_decoded = 411, tg = 14.75 t/s, tg_3s = 14.65 t/s
177.54.567.057 I slot print_timing: id 2 | task 76170 | n_decoded = 455, tg = 14.73 t/s, tg_3s = 14.50 t/s
177.57.628.136 I slot print_timing: id 2 | task 76170 | n_decoded = 501, tg = 14.75 t/s, tg_3s = 15.03 t/s
178.00.680.165 I slot print_timing: id 2 | task 76170 | n_decoded = 547, tg = 14.78 t/s, tg_3s = 15.07 t/s
178.02.221.107 I slot print_timing: id 2 | task 76170 | prompt eval time = 9187.84 ms / 264 tokens ( 34.80 ms per token, 28.73 tokens per second)
178.02.221.112 I slot print_timing: id 2 | task 76170 | eval time = 38547.97 ms / 570 tokens ( 67.63 ms per token, 14.79 tokens per second)
178.02.221.114 I slot print_timing: id 2 | task 76170 | total time = 47735.82 ms / 834 tokens
178.02.221.115 I slot print_timing: id 2 | task 76170 | graphs reused = 76094
178.02.230.307 I slot release: id 2 | task 76170 | stop processing: n_tokens = 208522, truncated = 0
178.03.698.154 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 0.998
178.03.706.675 I slot launch_slot_: id 2 | task 76742 | processing task, is_child = 0
178.16.163.202 I slot print_timing: id 2 | task 76742 | prompt processing, n_tokens = 639, progress = 1.00, t = 12.45 s / 51.31 tokens per second
178.23.093.252 I slot print_timing: id 2 | task 76742 | n_decoded = 100, tg = 14.99 t/s, tg_3s = 14.99 t/s
178.26.101.763 I slot print_timing: id 2 | task 76742 | n_decoded = 145, tg = 14.98 t/s, tg_3s = 14.96 t/s
178.29.136.781 I slot print_timing: id 2 | task 76742 | n_decoded = 190, tg = 14.94 t/s, tg_3s = 14.83 t/s
178.32.158.522 I slot print_timing: id 2 | task 76742 | n_decoded = 235, tg = 14.93 t/s, tg_3s = 14.89 t/s
178.35.174.190 I slot print_timing: id 2 | task 76742 | n_decoded = 280, tg = 14.93 t/s, tg_3s = 14.92 t/s
178.38.181.484 I slot print_timing: id 2 | task 76742 | n_decoded = 325, tg = 14.93 t/s, tg_3s = 14.96 t/s
178.41.240.602 I slot print_timing: id 2 | task 76742 | n_decoded = 371, tg = 14.95 t/s, tg_3s = 15.04 t/s
178.44.287.614 I slot print_timing: id 2 | task 76742 | n_decoded = 416, tg = 14.93 t/s, tg_3s = 14.77 t/s
178.47.293.880 I slot print_timing: id 2 | task 76742 | n_decoded = 461, tg = 14.93 t/s, tg_3s = 14.97 t/s
178.50.300.461 I slot print_timing: id 2 | task 76742 | n_decoded = 506, tg = 14.93 t/s, tg_3s = 14.97 t/s
178.53.330.717 I slot print_timing: id 2 | task 76742 | n_decoded = 551, tg = 14.93 t/s, tg_3s = 14.85 t/s
178.56.349.677 I slot print_timing: id 2 | task 76742 | n_decoded = 596, tg = 14.93 t/s, tg_3s = 14.91 t/s
178.59.039.647 I slot print_timing: id 2 | task 76742 | prompt eval time = 12711.41 ms / 643 tokens ( 19.77 ms per token, 50.58 tokens per second)
178.59.039.651 I slot print_timing: id 2 | task 76742 | eval time = 42619.59 ms / 636 tokens ( 67.01 ms per token, 14.92 tokens per second)
178.59.039.652 I slot print_timing: id 2 | task 76742 | total time = 55331.00 ms / 1279 tokens
178.59.039.654 I slot print_timing: id 2 | task 76742 | graphs reused = 76725
178.59.048.925 I slot release: id 2 | task 76742 | stop processing: n_tokens = 209227, truncated = 0
179.00.578.567 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.999
179.00.587.245 I slot launch_slot_: id 2 | task 77380 | processing task, is_child = 0
179.13.725.481 I slot print_timing: id 2 | task 77380 | prompt processing, n_tokens = 706, progress = 1.00, t = 13.14 s / 53.74 tokens per second
179.20.683.475 I slot print_timing: id 2 | task 77380 | n_decoded = 100, tg = 14.92 t/s, tg_3s = 14.92 t/s
179.23.689.568 I slot print_timing: id 2 | task 77380 | n_decoded = 145, tg = 14.94 t/s, tg_3s = 14.97 t/s
179.26.454.638 I slot print_timing: id 2 | task 77380 | prompt eval time = 13393.67 ms / 710 tokens ( 18.86 ms per token, 53.01 tokens per second)
179.26.454.643 I slot print_timing: id 2 | task 77380 | eval time = 12471.69 ms / 186 tokens ( 67.05 ms per token, 14.91 tokens per second)
179.26.454.662 I slot print_timing: id 2 | task 77380 | total time = 25865.36 ms / 896 tokens
179.26.454.664 I slot print_timing: id 2 | task 77380 | graphs reused = 76908
179.26.463.858 I slot release: id 2 | task 77380 | stop processing: n_tokens = 209483, truncated = 0
179.28.061.497 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.999
179.28.070.280 I slot launch_slot_: id 2 | task 77568 | processing task, is_child = 0
179.36.711.475 I slot print_timing: id 2 | task 77568 | prompt processing, n_tokens = 248, progress = 1.00, t = 8.64 s / 28.71 tokens per second
179.42.681.235 I slot print_timing: id 2 | task 77568 | prompt eval time = 8903.81 ms / 252 tokens ( 35.33 ms per token, 28.30 tokens per second)
179.42.681.240 I slot print_timing: id 2 | task 77568 | eval time = 5705.32 ms / 85 tokens ( 67.12 ms per token, 14.90 tokens per second)
179.42.681.241 I slot print_timing: id 2 | task 77568 | total time = 14609.13 ms / 337 tokens
179.42.681.243 I slot print_timing: id 2 | task 77568 | graphs reused = 76991
179.42.690.359 I slot release: id 2 | task 77568 | stop processing: n_tokens = 209630, truncated = 0
179.44.126.950 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 1.000
179.44.135.671 I slot launch_slot_: id 2 | task 77655 | processing task, is_child = 0
179.54.749.907 I slot print_timing: id 2 | task 77655 | prompt processing, n_tokens = 441, progress = 1.00, t = 10.61 s / 41.56 tokens per second
180.01.666.589 I slot print_timing: id 2 | task 77655 | n_decoded = 100, tg = 15.01 t/s, tg_3s = 15.01 t/s
180.04.713.584 I slot print_timing: id 2 | task 77655 | n_decoded = 145, tg = 14.94 t/s, tg_3s = 14.77 t/s
180.07.714.931 I slot print_timing: id 2 | task 77655 | n_decoded = 190, tg = 14.95 t/s, tg_3s = 14.99 t/s
180.07.951.744 I slot print_timing: id 2 | task 77655 | prompt eval time = 10867.39 ms / 445 tokens ( 24.42 ms per token, 40.95 tokens per second)
180.07.951.749 I slot print_timing: id 2 | task 77655 | eval time = 12946.76 ms / 193 tokens ( 67.08 ms per token, 14.91 tokens per second)
180.07.951.750 I slot print_timing: id 2 | task 77655 | total time = 23814.15 ms / 638 tokens
180.07.951.752 I slot print_timing: id 2 | task 77655 | graphs reused = 77181
180.07.960.686 I slot release: id 2 | task 77655 | stop processing: n_tokens = 210179, truncated = 0
180.09.469.945 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.999
180.09.478.415 I slot launch_slot_: id 2 | task 77850 | processing task, is_child = 0
180.18.360.624 I slot print_timing: id 2 | task 77850 | prompt processing, n_tokens = 255, progress = 1.00, t = 8.88 s / 28.72 tokens per second
180.25.282.826 I slot print_timing: id 2 | task 77850 | n_decoded = 100, tg = 15.01 t/s, tg_3s = 15.01 t/s
180.28.357.947 I slot print_timing: id 2 | task 77850 | n_decoded = 145, tg = 14.89 t/s, tg_3s = 14.63 t/s
180.31.414.817 I slot print_timing: id 2 | task 77850 | n_decoded = 189, tg = 14.77 t/s, tg_3s = 14.39 t/s
180.34.415.602 I slot print_timing: id 2 | task 77850 | n_decoded = 234, tg = 14.81 t/s, tg_3s = 15.00 t/s
180.37.479.403 I slot print_timing: id 2 | task 77850 | n_decoded = 280, tg = 14.85 t/s, tg_3s = 15.01 t/s
180.40.531.831 I slot print_timing: id 2 | task 77850 | n_decoded = 326, tg = 14.88 t/s, tg_3s = 15.07 t/s
180.43.593.071 I slot print_timing: id 2 | task 77850 | n_decoded = 372, tg = 14.90 t/s, tg_3s = 15.03 t/s
180.46.631.329 I slot print_timing: id 2 | task 77850 | n_decoded = 418, tg = 14.92 t/s, tg_3s = 15.14 t/s
180.49.685.451 I slot print_timing: id 2 | task 77850 | n_decoded = 464, tg = 14.94 t/s, tg_3s = 15.06 t/s
180.52.496.420 I slot print_timing: id 2 | task 77850 | prompt eval time = 9139.24 ms / 259 tokens ( 35.29 ms per token, 28.34 tokens per second)
180.52.496.425 I slot print_timing: id 2 | task 77850 | eval time = 33876.82 ms / 506 tokens ( 66.95 ms per token, 14.94 tokens per second)
180.52.496.426 I slot print_timing: id 2 | task 77850 | total time = 43016.07 ms / 765 tokens
180.52.496.428 I slot print_timing: id 2 | task 77850 | graphs reused = 77683
180.52.505.688 I slot release: id 2 | task 77850 | stop processing: n_tokens = 210747, truncated = 0
180.54.216.952 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.994 (> 0.100 thold), f_keep = 0.998
180.54.225.591 I slot launch_slot_: id 2 | task 78358 | processing task, is_child = 0
181.12.791.518 I slot print_timing: id 2 | task 78358 | prompt processing, n_tokens = 1468, progress = 1.00, t = 18.56 s / 79.08 tokens per second
181.19.758.881 I slot print_timing: id 2 | task 78358 | n_decoded = 100, tg = 14.92 t/s, tg_3s = 14.92 t/s
181.22.804.042 I slot print_timing: id 2 | task 78358 | n_decoded = 145, tg = 14.87 t/s, tg_3s = 14.78 t/s
181.23.822.100 I slot print_timing: id 2 | task 78358 | prompt eval time = 18826.91 ms / 1472 tokens ( 12.79 ms per token, 78.19 tokens per second)
181.23.822.105 I slot print_timing: id 2 | task 78358 | eval time = 10767.61 ms / 160 tokens ( 67.30 ms per token, 14.86 tokens per second)
181.23.822.106 I slot print_timing: id 2 | task 78358 | total time = 29594.53 ms / 1632 tokens
181.23.822.107 I slot print_timing: id 2 | task 78358 | graphs reused = 77840
181.23.830.842 I slot release: id 2 | task 78358 | stop processing: n_tokens = 211869, truncated = 0
181.25.295.630 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
181.25.304.188 I slot launch_slot_: id 2 | task 78520 | processing task, is_child = 0
181.35.365.189 I slot print_timing: id 2 | task 78520 | prompt processing, n_tokens = 306, progress = 1.00, t = 10.06 s / 30.42 tokens per second
181.42.275.382 I slot print_timing: id 2 | task 78520 | n_decoded = 100, tg = 15.05 t/s, tg_3s = 15.05 t/s
181.45.332.798 I slot print_timing: id 2 | task 78520 | n_decoded = 146, tg = 15.05 t/s, tg_3s = 15.05 t/s
181.48.398.063 I slot print_timing: id 2 | task 78520 | n_decoded = 192, tg = 15.04 t/s, tg_3s = 15.01 t/s
181.51.460.318 I slot print_timing: id 2 | task 78520 | n_decoded = 238, tg = 15.03 t/s, tg_3s = 15.02 t/s
181.54.513.822 I slot print_timing: id 2 | task 78520 | n_decoded = 284, tg = 15.04 t/s, tg_3s = 15.06 t/s
181.57.516.258 I slot print_timing: id 2 | task 78520 | n_decoded = 329, tg = 15.03 t/s, tg_3s = 14.99 t/s
182.00.555.698 I slot print_timing: id 2 | task 78520 | n_decoded = 375, tg = 15.04 t/s, tg_3s = 15.13 t/s
182.01.310.671 I slot print_timing: id 2 | task 78520 | prompt eval time = 10322.68 ms / 310 tokens ( 33.30 ms per token, 30.03 tokens per second)
182.01.310.676 I slot print_timing: id 2 | task 78520 | eval time = 25681.79 ms / 386 tokens ( 66.53 ms per token, 15.03 tokens per second)
182.01.310.677 I slot print_timing: id 2 | task 78520 | total time = 36004.47 ms / 696 tokens
182.01.310.679 I slot print_timing: id 2 | task 78520 | graphs reused = 78223
182.01.320.556 I slot release: id 2 | task 78520 | stop processing: n_tokens = 212401, truncated = 0
182.02.809.664 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 0.998
182.02.818.442 I slot launch_slot_: id 2 | task 78908 | processing task, is_child = 0
182.14.238.373 I slot print_timing: id 2 | task 78908 | prompt processing, n_tokens = 456, progress = 1.00, t = 11.42 s / 39.94 tokens per second
182.20.736.372 I slot print_timing: id 2 | task 78908 | prompt eval time = 11677.75 ms / 460 tokens ( 25.39 ms per token, 39.39 tokens per second)
182.20.736.376 I slot print_timing: id 2 | task 78908 | eval time = 6238.12 ms / 93 tokens ( 67.08 ms per token, 14.91 tokens per second)
182.20.736.377 I slot print_timing: id 2 | task 78908 | total time = 17915.88 ms / 553 tokens
182.20.736.379 I slot print_timing: id 2 | task 78908 | graphs reused = 78313
182.20.745.263 I slot release: id 2 | task 78908 | stop processing: n_tokens = 212564, truncated = 0
182.22.216.730 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 1.000
182.22.225.092 I slot launch_slot_: id 2 | task 79003 | processing task, is_child = 0
182.30.062.363 I slot print_timing: id 2 | task 79003 | prompt processing, n_tokens = 185, progress = 1.00, t = 7.84 s / 23.61 tokens per second
182.35.193.904 I slot print_timing: id 2 | task 79003 | prompt eval time = 8094.28 ms / 189 tokens ( 42.83 ms per token, 23.35 tokens per second)
182.35.193.913 I slot print_timing: id 2 | task 79003 | eval time = 4872.64 ms / 72 tokens ( 67.68 ms per token, 14.78 tokens per second)
182.35.193.914 I slot print_timing: id 2 | task 79003 | total time = 12966.92 ms / 261 tokens
182.35.193.935 I slot print_timing: id 2 | task 79003 | graphs reused = 78383
182.35.203.277 I slot release: id 2 | task 79003 | stop processing: n_tokens = 212728, truncated = 0
182.36.781.373 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 1.000
182.36.790.455 I slot launch_slot_: id 2 | task 79077 | processing task, is_child = 0
182.42.581.733 I slot print_timing: id 2 | task 79077 | prompt processing, n_tokens = 106, progress = 1.00, t = 5.79 s / 18.31 tokens per second
182.49.505.105 I slot print_timing: id 2 | task 79077 | n_decoded = 100, tg = 15.00 t/s, tg_3s = 15.00 t/s
182.52.523.619 I slot print_timing: id 2 | task 79077 | n_decoded = 145, tg = 14.97 t/s, tg_3s = 14.91 t/s
182.52.680.046 I slot print_timing: id 2 | task 79077 | prompt eval time = 6047.97 ms / 110 tokens ( 54.98 ms per token, 18.19 tokens per second)
182.52.680.051 I slot print_timing: id 2 | task 79077 | eval time = 9839.70 ms / 147 tokens ( 66.94 ms per token, 14.94 tokens per second)
182.52.680.053 I slot print_timing: id 2 | task 79077 | total time = 15887.67 ms / 257 tokens
182.52.680.054 I slot print_timing: id 2 | task 79077 | graphs reused = 78528
182.52.689.331 I slot release: id 2 | task 79077 | stop processing: n_tokens = 212909, truncated = 0
182.54.225.344 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.999
182.54.233.970 I slot launch_slot_: id 2 | task 79226 | processing task, is_child = 0
183.02.323.111 I slot print_timing: id 2 | task 79226 | prompt processing, n_tokens = 209, progress = 1.00, t = 8.09 s / 25.84 tokens per second
183.09.303.199 I slot print_timing: id 2 | task 79226 | n_decoded = 100, tg = 14.86 t/s, tg_3s = 14.86 t/s
183.09.726.535 I slot print_timing: id 2 | task 79226 | prompt eval time = 8339.10 ms / 213 tokens ( 39.15 ms per token, 25.54 tokens per second)
183.09.726.539 I slot print_timing: id 2 | task 79226 | eval time = 7151.35 ms / 106 tokens ( 67.47 ms per token, 14.82 tokens per second)
183.09.726.541 I slot print_timing: id 2 | task 79226 | total time = 15490.45 ms / 319 tokens
183.09.726.542 I slot print_timing: id 2 | task 79226 | graphs reused = 78631
183.09.736.145 I slot release: id 2 | task 79226 | stop processing: n_tokens = 213077, truncated = 0
183.11.297.897 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
183.11.306.487 I slot launch_slot_: id 2 | task 79334 | processing task, is_child = 0
183.21.304.978 I slot print_timing: id 2 | task 79334 | prompt processing, n_tokens = 361, progress = 1.00, t = 10.00 s / 36.11 tokens per second
183.28.225.134 I slot print_timing: id 2 | task 79334 | n_decoded = 100, tg = 15.02 t/s, tg_3s = 15.02 t/s
183.31.291.147 I slot print_timing: id 2 | task 79334 | n_decoded = 146, tg = 15.02 t/s, tg_3s = 15.00 t/s
183.33.663.314 I slot print_timing: id 2 | task 79334 | prompt eval time = 10259.45 ms / 365 tokens ( 28.11 ms per token, 35.58 tokens per second)
183.33.663.319 I slot print_timing: id 2 | task 79334 | eval time = 12095.42 ms / 180 tokens ( 67.20 ms per token, 14.88 tokens per second)
183.33.663.320 I slot print_timing: id 2 | task 79334 | total time = 22354.87 ms / 545 tokens
183.33.663.321 I slot print_timing: id 2 | task 79334 | graphs reused = 78808
183.33.672.311 I slot release: id 2 | task 79334 | stop processing: n_tokens = 213512, truncated = 0
183.35.280.829 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 1.000
183.35.289.519 I slot launch_slot_: id 2 | task 79516 | processing task, is_child = 0
183.49.767.763 I slot print_timing: id 2 | task 79516 | prompt processing, n_tokens = 786, progress = 1.00, t = 14.48 s / 54.30 tokens per second
183.56.708.727 I slot print_timing: id 2 | task 79516 | n_decoded = 100, tg = 14.96 t/s, tg_3s = 14.96 t/s
183.59.716.822 I slot print_timing: id 2 | task 79516 | n_decoded = 145, tg = 14.96 t/s, tg_3s = 14.96 t/s
184.02.742.297 I slot print_timing: id 2 | task 79516 | n_decoded = 190, tg = 14.94 t/s, tg_3s = 14.87 t/s
184.03.031.831 I slot print_timing: id 2 | task 79516 | prompt eval time = 14734.12 ms / 790 tokens ( 18.65 ms per token, 53.62 tokens per second)
184.03.031.836 I slot print_timing: id 2 | task 79516 | eval time = 13006.27 ms / 194 tokens ( 67.04 ms per token, 14.92 tokens per second)
184.03.031.837 I slot print_timing: id 2 | task 79516 | total time = 27740.39 ms / 984 tokens
184.03.031.839 I slot print_timing: id 2 | task 79516 | graphs reused = 78999
184.03.041.165 I slot release: id 2 | task 79516 | stop processing: n_tokens = 214312, truncated = 0
184.04.702.031 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
184.04.710.791 I slot launch_slot_: id 2 | task 79712 | processing task, is_child = 0
184.15.863.338 I slot print_timing: id 2 | task 79712 | prompt processing, n_tokens = 407, progress = 1.00, t = 11.15 s / 36.50 tokens per second
184.22.455.837 I slot print_timing: id 2 | task 79712 | prompt eval time = 11410.60 ms / 411 tokens ( 27.76 ms per token, 36.02 tokens per second)
184.22.455.841 I slot print_timing: id 2 | task 79712 | eval time = 6332.48 ms / 95 tokens ( 66.66 ms per token, 15.00 tokens per second)
184.22.455.843 I slot print_timing: id 2 | task 79712 | total time = 17743.08 ms / 506 tokens
184.22.455.844 I slot print_timing: id 2 | task 79712 | graphs reused = 79091
184.22.464.679 I slot release: id 2 | task 79712 | stop processing: n_tokens = 214620, truncated = 0
184.23.968.687 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
184.23.977.215 I slot launch_slot_: id 2 | task 79809 | processing task, is_child = 0
184.33.236.422 I slot print_timing: id 2 | task 79809 | prompt processing, n_tokens = 281, progress = 1.00, t = 9.26 s / 30.35 tokens per second
184.40.109.582 I slot print_timing: id 2 | task 79809 | n_decoded = 100, tg = 15.10 t/s, tg_3s = 15.10 t/s

{here also n repattion}

188.27.723.784 I slot print_timing: id 2 | task 79809 | n_decoded = 3401, tg = 14.52 t/s, tg_3s = 14.89 t/s
188.30.760.733 I slot print_timing: id 2 | task 79809 | n_decoded = 3447, tg = 14.53 t/s, tg_3s = 15.15 t/s
188.33.800.562 I slot print_timing: id 2 | task 79809 | n_decoded = 3493, tg = 14.54 t/s, tg_3s = 15.13 t/s
188.36.828.596 I slot print_timing: id 2 | task 79809 | n_decoded = 3539, tg = 14.54 t/s, tg_3s = 15.19 t/s
188.39.885.862 I slot print_timing: id 2 | task 79809 | n_decoded = 3584, tg = 14.55 t/s, tg_3s = 14.72 t/s
188.42.907.317 I slot print_timing: id 2 | task 79809 | n_decoded = 3629, tg = 14.55 t/s, tg_3s = 14.89 t/s
188.45.922.353 I slot print_timing: id 2 | task 79809 | n_decoded = 3674, tg = 14.55 t/s, tg_3s = 14.93 t/s
188.48.923.498 I slot print_timing: id 2 | task 79809 | n_decoded = 3719, tg = 14.56 t/s, tg_3s = 14.99 t/s
188.51.988.459 I slot print_timing: id 2 | task 79809 | n_decoded = 3765, tg = 14.56 t/s, tg_3s = 15.01 t/s
188.55.052.684 I slot print_timing: id 2 | task 79809 | n_decoded = 3811, tg = 14.57 t/s, tg_3s = 15.01 t/s
188.58.110.972 I slot print_timing: id 2 | task 79809 | n_decoded = 3857, tg = 14.58 t/s, tg_3s = 15.04 t/s
188.59.724.681 W srv stop: cancel task, id_task = 79809
188.59.791.087 I slot release: id 2 | task 79809 | stop processing: n_tokens = 218688, truncated = 0
189.06.919.753 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 0.981
189.06.928.882 I slot launch_slot_: id 2 | task 83694 | processing task, is_child = 0
189.12.900.393 I slot print_timing: id 2 | task 83694 | prompt processing, n_tokens = 100, progress = 1.00, t = 5.97 s / 16.75 tokens per second
189.20.118.359 I slot print_timing: id 2 | task 83694 | prompt processing, n_tokens = 295, progress = 1.00, t = 13.19 s / 22.37 tokens per second
189.27.039.232 I slot print_timing: id 2 | task 83694 | n_decoded = 100, tg = 15.00 t/s, tg_3s = 15.00 t/s
189.30.056.027 I slot print_timing: id 2 | task 83694 | n_decoded = 145, tg = 14.97 t/s, tg_3s = 14.92 t/s
189.33.076.774 I slot print_timing: id 2 | task 83694 | n_decoded = 190, tg = 14.96 t/s, tg_3s = 14.90 t/s
189.36.100.939 I slot print_timing: id 2 | task 83694 | n_decoded = 235, tg = 14.94 t/s, tg_3s = 14.88 t/s
189.39.143.967 I slot print_timing: id 2 | task 83694 | n_decoded = 280, tg = 14.92 t/s, tg_3s = 14.79 t/s
189.42.185.957 I slot print_timing: id 2 | task 83694 | n_decoded = 325, tg = 14.90 t/s, tg_3s = 14.79 t/s
189.45.251.884 I slot print_timing: id 2 | task 83694 | n_decoded = 371, tg = 14.91 t/s, tg_3s = 15.00 t/s
189.48.303.253 I slot print_timing: id 2 | task 83694 | n_decoded = 416, tg = 14.89 t/s, tg_3s = 14.75 t/s
189.51.348.524 I slot print_timing: id 2 | task 83694 | n_decoded = 461, tg = 14.88 t/s, tg_3s = 14.78 t/s
189.54.400.870 I slot print_timing: id 2 | task 83694 | n_decoded = 505, tg = 14.84 t/s, tg_3s = 14.42 t/s
189.57.441.145 I slot print_timing: id 2 | task 83694 | n_decoded = 549, tg = 14.81 t/s, tg_3s = 14.47 t/s
190.00.466.820 I slot print_timing: id 2 | task 83694 | n_decoded = 594, tg = 14.82 t/s, tg_3s = 14.87 t/s
190.03.510.674 I slot print_timing: id 2 | task 83694 | n_decoded = 639, tg = 14.81 t/s, tg_3s = 14.78 t/s
190.06.536.799 I slot print_timing: id 2 | task 83694 | n_decoded = 684, tg = 14.82 t/s, tg_3s = 14.87 t/s
190.09.553.886 I slot print_timing: id 2 | task 83694 | n_decoded = 729, tg = 14.82 t/s, tg_3s = 14.92 t/s
190.11.373.424 I slot print_timing: id 2 | task 83694 | prompt eval time = 13442.07 ms / 299 tokens ( 44.96 ms per token, 22.24 tokens per second)
190.11.373.428 I slot print_timing: id 2 | task 83694 | eval time = 51000.20 ms / 755 tokens ( 67.55 ms per token, 14.80 tokens per second)
190.11.373.430 I slot print_timing: id 2 | task 83694 | total time = 64442.27 ms / 1054 tokens
190.11.373.432 I slot print_timing: id 2 | task 83694 | graphs reused = 83706
190.11.383.209 I slot release: id 2 | task 83694 | stop processing: n_tokens = 215575, truncated = 0
190.12.936.525 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 0.999
190.12.945.504 I slot launch_slot_: id 2 | task 84452 | processing task, is_child = 0
190.26.931.563 I slot print_timing: id 2 | task 84452 | prompt processing, n_tokens = 825, progress = 1.00, t = 13.98 s / 59.00 tokens per second
190.34.053.328 I slot print_timing: id 2 | task 84452 | n_decoded = 100, tg = 14.57 t/s, tg_3s = 14.57 t/s
190.37.077.351 I slot print_timing: id 2 | task 84452 | prompt eval time = 14244.54 ms / 829 tokens ( 17.18 ms per token, 58.20 tokens per second)
190.37.077.357 I slot print_timing: id 2 | task 84452 | eval time = 9885.27 ms / 143 tokens ( 69.13 ms per token, 14.47 tokens per second)
190.37.077.358 I slot print_timing: id 2 | task 84452 | total time = 24129.81 ms / 972 tokens
190.37.077.360 I slot print_timing: id 2 | task 84452 | graphs reused = 83847
190.37.087.328 I slot release: id 2 | task 84452 | stop processing: n_tokens = 215788, truncated = 0
190.38.747.235 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
190.38.756.860 I slot launch_slot_: id 2 | task 84597 | processing task, is_child = 0
190.45.478.348 I slot print_timing: id 2 | task 84597 | prompt processing, n_tokens = 192, progress = 1.00, t = 6.72 s / 28.57 tokens per second
190.51.994.037 I slot print_timing: id 2 | task 84597 | prompt eval time = 6969.01 ms / 196 tokens ( 35.56 ms per token, 28.12 tokens per second)
190.51.994.042 I slot print_timing: id 2 | task 84597 | eval time = 6266.28 ms / 92 tokens ( 68.11 ms per token, 14.68 tokens per second)
190.51.994.043 I slot print_timing: id 2 | task 84597 | total time = 13235.29 ms / 288 tokens
190.51.994.045 I slot print_timing: id 2 | task 84597 | graphs reused = 83937
190.52.003.579 I slot release: id 2 | task 84597 | stop processing: n_tokens = 215929, truncated = 0
190.53.656.187 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 1.000
190.53.665.379 I slot launch_slot_: id 2 | task 84691 | processing task, is_child = 0
190.59.604.815 I slot print_timing: id 2 | task 84691 | prompt processing, n_tokens = 125, progress = 1.00, t = 5.94 s / 21.05 tokens per second
191.06.554.739 I slot print_timing: id 2 | task 84691 | n_decoded = 100, tg = 14.96 t/s, tg_3s = 14.96 t/s
191.09.587.457 I slot print_timing: id 2 | task 84691 | n_decoded = 145, tg = 14.92 t/s, tg_3s = 14.84 t/s
191.10.662.789 I slot print_timing: id 2 | task 84691 | prompt eval time = 6202.67 ms / 129 tokens ( 48.08 ms per token, 20.80 tokens per second)
191.10.662.794 I slot print_timing: id 2 | task 84691 | eval time = 10792.63 ms / 160 tokens ( 67.45 ms per token, 14.82 tokens per second)
191.10.662.795 I slot print_timing: id 2 | task 84691 | total time = 16995.30 ms / 289 tokens
191.10.662.797 I slot print_timing: id 2 | task 84691 | graphs reused = 84094
191.10.672.705 I slot release: id 2 | task 84691 | stop processing: n_tokens = 216122, truncated = 0
191.13.232.366 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
191.13.241.191 I slot launch_slot_: id 2 | task 84853 | processing task, is_child = 0
191.22.341.267 I slot print_timing: id 2 | task 84853 | prompt processing, n_tokens = 285, progress = 1.00, t = 9.10 s / 31.32 tokens per second
191.29.247.324 I slot print_timing: id 2 | task 84853 | n_decoded = 100, tg = 15.02 t/s, tg_3s = 15.02 t/s
191.32.279.922 I slot print_timing: id 2 | task 84853 | n_decoded = 145, tg = 14.97 t/s, tg_3s = 14.84 t/s
191.35.286.872 I slot print_timing: id 2 | task 84853 | n_decoded = 190, tg = 14.97 t/s, tg_3s = 14.97 t/s
191.38.300.487 I slot print_timing: id 2 | task 84853 | n_decoded = 235, tg = 14.96 t/s, tg_3s = 14.93 t/s
191.41.309.223 I slot print_timing: id 2 | task 84853 | n_decoded = 280, tg = 14.96 t/s, tg_3s = 14.96 t/s
191.44.372.071 I slot print_timing: id 2 | task 84853 | n_decoded = 326, tg = 14.97 t/s, tg_3s = 15.02 t/s
191.47.403.432 I slot print_timing: id 2 | task 84853 | n_decoded = 371, tg = 14.95 t/s, tg_3s = 14.84 t/s
191.50.425.216 I slot print_timing: id 2 | task 84853 | n_decoded = 416, tg = 14.95 t/s, tg_3s = 14.89 t/s
191.53.459.600 I slot print_timing: id 2 | task 84853 | n_decoded = 461, tg = 14.93 t/s, tg_3s = 14.83 t/s
191.56.500.246 I slot print_timing: id 2 | task 84853 | n_decoded = 506, tg = 14.92 t/s, tg_3s = 14.80 t/s
191.59.527.147 I slot print_timing: id 2 | task 84853 | n_decoded = 551, tg = 14.92 t/s, tg_3s = 14.87 t/s
192.02.555.409 I slot print_timing: id 2 | task 84853 | n_decoded = 596, tg = 14.91 t/s, tg_3s = 14.86 t/s
192.05.628.913 I slot print_timing: id 2 | task 84853 | n_decoded = 640, tg = 14.87 t/s, tg_3s = 14.32 t/s
192.08.682.229 I slot print_timing: id 2 | task 84853 | n_decoded = 683, tg = 14.82 t/s, tg_3s = 14.08 t/s
192.11.711.907 I slot print_timing: id 2 | task 84853 | n_decoded = 727, tg = 14.80 t/s, tg_3s = 14.52 t/s
192.12.006.032 I slot print_timing: id 2 | task 84853 | prompt eval time = 9347.61 ms / 289 tokens ( 32.34 ms per token, 30.92 tokens per second)
192.12.006.037 I slot print_timing: id 2 | task 84853 | eval time = 49415.35 ms / 731 tokens ( 67.60 ms per token, 14.79 tokens per second)
192.12.006.038 I slot print_timing: id 2 | task 84853 | total time = 58762.96 ms / 1020 tokens
192.12.006.040 I slot print_timing: id 2 | task 84853 | graphs reused = 84820
192.12.016.414 I slot release: id 2 | task 84853 | stop processing: n_tokens = 216978, truncated = 0
192.13.591.145 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.996 (> 0.100 thold), f_keep = 1.000
192.13.601.311 I slot launch_slot_: id 2 | task 85586 | processing task, is_child = 0
192.32.604.639 I slot print_timing: id 2 | task 85586 | prompt processing, n_tokens = 1413, progress = 1.00, t = 19.00 s / 74.36 tokens per second
192.39.582.995 I slot print_timing: id 2 | task 85586 | n_decoded = 100, tg = 14.88 t/s, tg_3s = 14.88 t/s
192.42.595.155 I slot print_timing: id 2 | task 85586 | n_decoded = 145, tg = 14.90 t/s, tg_3s = 14.94 t/s
192.43.427.308 I slot print_timing: id 2 | task 85586 | prompt eval time = 19256.91 ms / 1417 tokens ( 13.59 ms per token, 73.58 tokens per second)
192.43.427.329 I slot print_timing: id 2 | task 85586 | eval time = 10566.65 ms / 157 tokens ( 67.30 ms per token, 14.86 tokens per second)
192.43.427.330 I slot print_timing: id 2 | task 85586 | total time = 29823.56 ms / 1574 tokens
192.43.427.332 I slot print_timing: id 2 | task 85586 | graphs reused = 84975
192.43.436.606 I slot release: id 2 | task 85586 | stop processing: n_tokens = 217817, truncated = 0
192.45.162.012 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
192.45.170.761 I slot launch_slot_: id 2 | task 85745 | processing task, is_child = 0
192.54.571.205 I slot print_timing: id 2 | task 85745 | prompt processing, n_tokens = 289, progress = 1.00, t = 9.40 s / 30.75 tokens per second
192.59.629.661 I slot print_timing: id 2 | task 85745 | prompt eval time = 9652.24 ms / 293 tokens ( 32.94 ms per token, 30.36 tokens per second)
192.59.629.665 I slot print_timing: id 2 | task 85745 | eval time = 4804.63 ms / 69 tokens ( 69.63 ms per token, 14.36 tokens per second)
192.59.629.667 I slot print_timing: id 2 | task 85745 | total time = 14456.87 ms / 362 tokens
192.59.629.669 I slot print_timing: id 2 | task 85745 | graphs reused = 85042
192.59.639.971 I slot release: id 2 | task 85745 | stop processing: n_tokens = 218018, truncated = 0
193.01.176.222 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.954 (> 0.100 thold), f_keep = 1.000
193.01.185.738 I slot launch_slot_: id 2 | task 85816 | processing task, is_child = 0
193.22.181.015 I slot print_timing: id 2 | task 85816 | prompt processing, n_tokens = 2016, progress = 0.96, t = 20.99 s / 96.03 tokens per second
194.23.077.976 I slot print_timing: id 2 | task 85816 | prompt processing, n_tokens = 10512, progress = 1.00, t = 81.89 s / 128.37 tokens per second
194.30.133.273 I slot print_timing: id 2 | task 85816 | n_decoded = 100, tg = 14.72 t/s, tg_3s = 14.72 t/s
194.32.392.226 I slot print_timing: id 2 | task 85816 | prompt eval time = 82153.57 ms / 10516 tokens ( 7.81 ms per token, 128.00 tokens per second)
194.32.392.231 I slot print_timing: id 2 | task 85816 | eval time = 9051.00 ms / 133 tokens ( 68.05 ms per token, 14.69 tokens per second)
194.32.392.232 I slot print_timing: id 2 | task 85816 | total time = 91204.56 ms / 10649 tokens
194.32.392.234 I slot print_timing: id 2 | task 85816 | graphs reused = 85173
194.32.402.272 I slot release: id 2 | task 85816 | stop processing: n_tokens = 228594, truncated = 0
194.34.180.241 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.998 (> 0.100 thold), f_keep = 1.000
194.34.188.739 I slot launch_slot_: id 2 | task 85952 | processing task, is_child = 0
194.45.100.619 I slot print_timing: id 2 | task 85952 | prompt processing, n_tokens = 443, progress = 1.00, t = 10.91 s / 40.61 tokens per second
194.52.214.155 I slot print_timing: id 2 | task 85952 | n_decoded = 100, tg = 14.60 t/s, tg_3s = 14.60 t/s
194.54.017.425 I slot print_timing: id 2 | task 85952 | prompt eval time = 11174.20 ms / 447 tokens ( 25.00 ms per token, 40.00 tokens per second)
194.54.017.430 I slot print_timing: id 2 | task 85952 | eval time = 8651.93 ms / 126 tokens ( 68.67 ms per token, 14.56 tokens per second)
194.54.017.431 I slot print_timing: id 2 | task 85952 | total time = 19826.14 ms / 573 tokens
194.54.017.433 I slot print_timing: id 2 | task 85952 | graphs reused = 85297
194.54.026.906 I slot release: id 2 | task 85952 | stop processing: n_tokens = 229030, truncated = 0
194.55.712.921 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
194.55.721.561 I slot launch_slot_: id 2 | task 86080 | processing task, is_child = 0
195.03.278.546 I slot print_timing: id 2 | task 86080 | prompt processing, n_tokens = 197, progress = 1.00, t = 7.56 s / 26.08 tokens per second
195.10.399.190 I slot print_timing: id 2 | task 86080 | n_decoded = 100, tg = 14.57 t/s, tg_3s = 14.57 t/s
195.12.186.094 I slot print_timing: id 2 | task 86080 | prompt eval time = 7813.34 ms / 201 tokens ( 38.87 ms per token, 25.73 tokens per second)
195.12.186.099 I slot print_timing: id 2 | task 86080 | eval time = 8649.19 ms / 126 tokens ( 68.64 ms per token, 14.57 tokens per second)
195.12.186.100 I slot print_timing: id 2 | task 86080 | total time = 16462.54 ms / 327 tokens
195.12.186.102 I slot print_timing: id 2 | task 86080 | graphs reused = 85420
195.12.196.182 I slot release: id 2 | task 86080 | stop processing: n_tokens = 229227, truncated = 0
195.13.959.539 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
195.13.969.532 I slot launch_slot_: id 2 | task 86208 | processing task, is_child = 0
195.22.436.757 I slot print_timing: id 2 | task 86208 | prompt processing, n_tokens = 256, progress = 1.00, t = 8.47 s / 30.24 tokens per second
195.27.925.469 I slot print_timing: id 2 | task 86208 | prompt eval time = 8730.92 ms / 260 tokens ( 33.58 ms per token, 29.78 tokens per second)
195.27.925.474 I slot print_timing: id 2 | task 86208 | eval time = 5222.94 ms / 76 tokens ( 68.72 ms per token, 14.55 tokens per second)
195.27.925.476 I slot print_timing: id 2 | task 86208 | total time = 13953.87 ms / 336 tokens
195.27.925.477 I slot print_timing: id 2 | task 86208 | graphs reused = 85493
195.27.935.259 I slot release: id 2 | task 86208 | stop processing: n_tokens = 229433, truncated = 0
195.30.668.479 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.951 (> 0.100 thold), f_keep = 1.000
195.30.677.376 I slot launch_slot_: id 2 | task 86286 | processing task, is_child = 0
196.00.118.155 I slot print_timing: id 2 | task 86286 | prompt processing, n_tokens = 3273, progress = 0.96, t = 29.44 s / 111.18 tokens per second
197.02.927.940 I slot print_timing: id 2 | task 86286 | prompt processing, n_tokens = 11769, progress = 1.00, t = 92.25 s / 127.58 tokens per second
197.10.055.994 I slot print_timing: id 2 | task 86286 | n_decoded = 100, tg = 14.56 t/s, tg_3s = 14.56 t/s
197.13.112.141 I slot print_timing: id 2 | task 86286 | n_decoded = 144, tg = 14.51 t/s, tg_3s = 14.40 t/s
197.14.927.711 I slot print_timing: id 2 | task 86286 | prompt eval time = 92506.15 ms / 11773 tokens ( 7.86 ms per token, 127.27 tokens per second)
197.14.927.715 I slot print_timing: id 2 | task 86286 | eval time = 11741.77 ms / 170 tokens ( 69.07 ms per token, 14.48 tokens per second)
197.14.927.717 I slot print_timing: id 2 | task 86286 | total time = 104247.93 ms / 11943 tokens
197.14.927.719 I slot print_timing: id 2 | task 86286 | graphs reused = 85660
197.14.938.747 I slot release: id 2 | task 86286 | stop processing: n_tokens = 241296, truncated = 0
197.19.940.452 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
197.19.949.597 I slot launch_slot_: id 2 | task 86459 | processing task, is_child = 0
197.28.623.615 I slot print_timing: id 2 | task 86459 | prompt processing, n_tokens = 240, progress = 1.00, t = 8.67 s / 27.68 tokens per second
197.35.726.778 I slot print_timing: id 2 | task 86459 | n_decoded = 100, tg = 14.62 t/s, tg_3s = 14.62 t/s
197.38.775.511 I slot print_timing: id 2 | task 86459 | n_decoded = 143, tg = 14.46 t/s, tg_3s = 14.10 t/s
197.41.785.367 I slot print_timing: id 2 | task 86459 | n_decoded = 187, tg = 14.50 t/s, tg_3s = 14.62 t/s
197.43.673.983 I slot print_timing: id 2 | task 86459 | prompt eval time = 8934.73 ms / 244 tokens ( 36.62 ms per token, 27.31 tokens per second)
197.43.673.988 I slot print_timing: id 2 | task 86459 | eval time = 14787.50 ms / 214 tokens ( 69.10 ms per token, 14.47 tokens per second)
197.43.673.989 I slot print_timing: id 2 | task 86459 | total time = 23722.23 ms / 458 tokens
197.43.673.991 I slot print_timing: id 2 | task 86459 | graphs reused = 85871
197.43.684.441 I slot release: id 2 | task 86459 | stop processing: n_tokens = 241580, truncated = 0
197.45.317.532 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 1.000
197.45.326.367 I slot launch_slot_: id 2 | task 86675 | processing task, is_child = 0
197.59.777.831 I slot print_timing: id 2 | task 86675 | prompt processing, n_tokens = 801, progress = 1.00, t = 14.45 s / 55.44 tokens per second
198.06.916.510 I slot print_timing: id 2 | task 86675 | n_decoded = 100, tg = 14.55 t/s, tg_3s = 14.55 t/s
198.09.970.622 I slot print_timing: id 2 | task 86675 | prompt eval time = 14715.62 ms / 805 tokens ( 18.28 ms per token, 54.70 tokens per second)
198.09.970.626 I slot print_timing: id 2 | task 86675 | eval time = 9926.25 ms / 144 tokens ( 68.93 ms per token, 14.51 tokens per second)
198.09.970.628 I slot print_timing: id 2 | task 86675 | total time = 24641.87 ms / 949 tokens
198.09.970.629 I slot print_timing: id 2 | task 86675 | graphs reused = 86012
198.09.981.196 I slot release: id 2 | task 86675 | stop processing: n_tokens = 242311, truncated = 0
198.11.653.130 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
198.11.662.200 I slot launch_slot_: id 2 | task 86821 | processing task, is_child = 0
198.19.852.977 I slot print_timing: id 2 | task 86821 | prompt processing, n_tokens = 238, progress = 1.00, t = 8.19 s / 29.07 tokens per second
198.27.019.765 I slot print_timing: id 2 | task 86821 | n_decoded = 100, tg = 14.49 t/s, tg_3s = 14.49 t/s
198.30.036.377 I slot print_timing: id 2 | task 86821 | n_decoded = 143, tg = 14.42 t/s, tg_3s = 14.25 t/s
198.33.077.706 I slot print_timing: id 2 | task 86821 | n_decoded = 187, tg = 14.43 t/s, tg_3s = 14.47 t/s
198.35.578.086 I slot print_timing: id 2 | task 86821 | prompt eval time = 8456.02 ms / 242 tokens ( 34.94 ms per token, 28.62 tokens per second)
198.35.578.091 I slot print_timing: id 2 | task 86821 | eval time = 15457.46 ms / 223 tokens ( 69.32 ms per token, 14.43 tokens per second)
198.35.578.092 I slot print_timing: id 2 | task 86821 | total time = 23913.48 ms / 465 tokens
198.35.578.094 I slot print_timing: id 2 | task 86821 | graphs reused = 86232
198.35.588.159 I slot release: id 2 | task 86821 | stop processing: n_tokens = 242628, truncated = 0
198.37.381.015 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
198.37.390.037 I slot launch_slot_: id 2 | task 87046 | processing task, is_child = 0
198.46.149.681 I slot print_timing: id 2 | task 87046 | prompt processing, n_tokens = 247, progress = 1.00, t = 8.76 s / 28.21 tokens per second
198.53.380.504 I slot print_timing: id 2 | task 87046 | n_decoded = 100, tg = 14.34 t/s, tg_3s = 14.34 t/s
198.56.380.708 I slot print_timing: id 2 | task 87046 | n_decoded = 144, tg = 14.44 t/s, tg_3s = 14.67 t/s
198.56.674.589 I slot print_timing: id 2 | task 87046 | prompt eval time = 9015.90 ms / 251 tokens ( 35.92 ms per token, 27.84 tokens per second)
198.56.674.594 I slot print_timing: id 2 | task 87046 | eval time = 10266.13 ms / 148 tokens ( 69.37 ms per token, 14.42 tokens per second)
198.56.674.595 I slot print_timing: id 2 | task 87046 | total time = 19282.03 ms / 399 tokens
198.56.674.597 I slot print_timing: id 2 | task 87046 | graphs reused = 86377
198.56.685.025 I slot release: id 2 | task 87046 | stop processing: n_tokens = 242800, truncated = 0
198.58.312.893 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
198.58.321.093 I slot launch_slot_: id 2 | task 87196 | processing task, is_child = 0
199.06.664.951 I slot print_timing: id 2 | task 87196 | prompt processing, n_tokens = 213, progress = 1.00, t = 8.34 s / 25.53 tokens per second
199.13.797.279 I slot print_timing: id 2 | task 87196 | n_decoded = 100, tg = 14.55 t/s, tg_3s = 14.55 t/s
199.16.797.908 I slot print_timing: id 2 | task 87196 | n_decoded = 143, tg = 14.49 t/s, tg_3s = 14.33 t/s
199.16.868.539 I slot print_timing: id 2 | task 87196 | prompt eval time = 8602.55 ms / 217 tokens ( 39.64 ms per token, 25.23 tokens per second)
199.16.868.544 I slot print_timing: id 2 | task 87196 | eval time = 9942.67 ms / 144 tokens ( 69.05 ms per token, 14.48 tokens per second)
199.16.868.545 I slot print_timing: id 2 | task 87196 | total time = 18545.22 ms / 361 tokens
199.16.868.547 I slot print_timing: id 2 | task 87196 | graphs reused = 86518
199.16.878.777 I slot release: id 2 | task 87196 | stop processing: n_tokens = 243009, truncated = 0
199.18.710.196 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.996 (> 0.100 thold), f_keep = 1.000
199.18.719.716 I slot launch_slot_: id 2 | task 87342 | processing task, is_child = 0
199.33.897.029 I slot print_timing: id 2 | task 87342 | prompt processing, n_tokens = 906, progress = 1.00, t = 15.17 s / 59.70 tokens per second
199.40.993.006 I slot print_timing: id 2 | task 87342 | n_decoded = 100, tg = 14.65 t/s, tg_3s = 14.65 t/s
199.44.058.121 I slot print_timing: id 2 | task 87342 | n_decoded = 145, tg = 14.66 t/s, tg_3s = 14.68 t/s
199.47.100.491 I slot print_timing: id 2 | task 87342 | n_decoded = 188, tg = 14.54 t/s, tg_3s = 14.13 t/s
199.50.120.403 I slot print_timing: id 2 | task 87342 | n_decoded = 232, tg = 14.54 t/s, tg_3s = 14.57 t/s
199.53.136.750 I slot print_timing: id 2 | task 87342 | n_decoded = 276, tg = 14.55 t/s, tg_3s = 14.59 t/s
199.53.778.439 I slot print_timing: id 2 | task 87342 | prompt eval time = 15445.14 ms / 910 tokens ( 16.97 ms per token, 58.92 tokens per second)
199.53.778.444 I slot print_timing: id 2 | task 87342 | eval time = 19610.97 ms / 285 tokens ( 68.81 ms per token, 14.53 tokens per second)
199.53.778.461 I slot print_timing: id 2 | task 87342 | total time = 35056.11 ms / 1195 tokens
199.53.778.463 I slot print_timing: id 2 | task 87342 | graphs reused = 86800
199.53.788.651 I slot release: id 2 | task 87342 | stop processing: n_tokens = 244056, truncated = 0
199.57.048.232 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.996 (> 0.100 thold), f_keep = 0.999
199.57.057.479 I slot launch_slot_: id 2 | task 87629 | processing task, is_child = 0
200.12.464.269 I slot print_timing: id 2 | task 87629 | prompt processing, n_tokens = 924, progress = 1.00, t = 15.40 s / 59.98 tokens per second
200.19.604.081 I slot print_timing: id 2 | task 87629 | n_decoded = 100, tg = 14.53 t/s, tg_3s = 14.53 t/s
200.21.346.783 I slot print_timing: id 2 | task 87629 | prompt eval time = 15660.52 ms / 928 tokens ( 16.88 ms per token, 59.26 tokens per second)
200.21.346.787 I slot print_timing: id 2 | task 87629 | eval time = 8626.37 ms / 125 tokens ( 69.01 ms per token, 14.49 tokens per second)
200.21.346.789 I slot print_timing: id 2 | task 87629 | total time = 24286.89 ms / 1053 tokens
200.21.346.790 I slot print_timing: id 2 | task 87629 | graphs reused = 86922
200.21.357.071 I slot release: id 2 | task 87629 | stop processing: n_tokens = 244820, truncated = 0
200.23.134.821 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
200.23.143.637 I slot launch_slot_: id 2 | task 87756 | processing task, is_child = 0
200.32.980.297 I slot print_timing: id 2 | task 87756 | prompt processing, n_tokens = 293, progress = 1.00, t = 9.83 s / 29.79 tokens per second
200.40.186.676 I slot print_timing: id 2 | task 87756 | n_decoded = 100, tg = 14.44 t/s, tg_3s = 14.44 t/s
200.43.219.847 I slot print_timing: id 2 | task 87756 | n_decoded = 144, tg = 14.46 t/s, tg_3s = 14.51 t/s
200.43.864.132 I slot print_timing: id 2 | task 87756 | prompt eval time = 10117.14 ms / 297 tokens ( 34.06 ms per token, 29.36 tokens per second)
200.43.864.137 I slot print_timing: id 2 | task 87756 | eval time = 10600.94 ms / 153 tokens ( 69.29 ms per token, 14.43 tokens per second)
200.43.864.138 I slot print_timing: id 2 | task 87756 | total time = 20718.08 ms / 450 tokens
200.43.864.140 I slot print_timing: id 2 | task 87756 | graphs reused = 87072
200.43.874.538 I slot release: id 2 | task 87756 | stop processing: n_tokens = 245141, truncated = 0
200.45.703.367 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
200.45.712.738 I slot launch_slot_: id 2 | task 87911 | processing task, is_child = 0
200.53.645.616 I slot print_timing: id 2 | task 87911 | prompt processing, n_tokens = 223, progress = 1.00, t = 7.93 s / 28.12 tokens per second
201.00.812.581 I slot print_timing: id 2 | task 87911 | n_decoded = 100, tg = 14.49 t/s, tg_3s = 14.49 t/s
201.03.194.478 I slot print_timing: id 2 | task 87911 | prompt eval time = 8198.13 ms / 227 tokens ( 36.12 ms per token, 27.69 tokens per second)
201.03.194.499 I slot print_timing: id 2 | task 87911 | eval time = 9281.13 ms / 134 tokens ( 69.26 ms per token, 14.44 tokens per second)
201.03.194.501 I slot print_timing: id 2 | task 87911 | total time = 17479.26 ms / 361 tokens
201.03.194.502 I slot print_timing: id 2 | task 87911 | graphs reused = 87203
201.03.205.124 I slot release: id 2 | task 87911 | stop processing: n_tokens = 245345, truncated = 0
201.05.109.251 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
201.05.118.723 I slot launch_slot_: id 2 | task 88047 | processing task, is_child = 0
201.13.934.272 I slot print_timing: id 2 | task 88047 | prompt processing, n_tokens = 265, progress = 1.00, t = 8.81 s / 30.07 tokens per second
201.18.934.411 I slot print_timing: id 2 | task 88047 | prompt eval time = 9085.52 ms / 269 tokens ( 33.78 ms per token, 29.61 tokens per second)
201.18.934.433 I slot print_timing: id 2 | task 88047 | eval time = 4727.68 ms / 68 tokens ( 69.52 ms per token, 14.38 tokens per second)
201.18.934.434 I slot print_timing: id 2 | task 88047 | total time = 13813.21 ms / 337 tokens
201.18.934.436 I slot print_timing: id 2 | task 88047 | graphs reused = 87268
201.18.945.322 I slot release: id 2 | task 88047 | stop processing: n_tokens = 245544, truncated = 0
204.04.771.346 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.955 (> 0.100 thold), f_keep = 1.000
204.04.780.623 I slot launch_slot_: id 2 | task 88117 | processing task, is_child = 0
204.33.330.547 I slot print_timing: id 2 | task 88117 | prompt processing, n_tokens = 2989, progress = 0.97, t = 28.55 s / 104.70 tokens per second
205.38.893.786 I slot print_timing: id 2 | task 88117 | prompt processing, n_tokens = 11485, progress = 1.00, t = 94.11 s / 122.04 tokens per second
205.46.220.559 I slot print_timing: id 2 | task 88117 | n_decoded = 100, tg = 14.17 t/s, tg_3s = 14.17 t/s
205.49.044.365 I slot print_timing: id 2 | task 88117 | prompt eval time = 94381.78 ms / 11489 tokens ( 8.21 ms per token, 121.73 tokens per second)
205.49.044.385 I slot print_timing: id 2 | task 88117 | eval time = 9879.50 ms / 140 tokens ( 70.57 ms per token, 14.17 tokens per second)
205.49.044.387 I slot print_timing: id 2 | task 88117 | total time = 104261.28 ms / 11629 tokens
205.49.044.388 I slot print_timing: id 2 | task 88117 | graphs reused = 87405
205.49.055.703 I slot release: id 2 | task 88117 | stop processing: n_tokens = 257101, truncated = 0
205.51.482.488 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
205.51.491.514 I slot launch_slot_: id 2 | task 88260 | processing task, is_child = 0
205.59.598.604 I slot print_timing: id 2 | task 88260 | prompt processing, n_tokens = 210, progress = 1.00, t = 8.10 s / 25.91 tokens per second
206.06.816.116 I slot print_timing: id 2 | task 88260 | n_decoded = 100, tg = 14.41 t/s, tg_3s = 14.41 t/s
206.09.827.008 I slot print_timing: id 2 | task 88260 | n_decoded = 143, tg = 14.37 t/s, tg_3s = 14.28 t/s
206.12.876.971 I slot print_timing: id 2 | task 88260 | n_decoded = 187, tg = 14.38 t/s, tg_3s = 14.43 t/s
206.15.925.294 I slot print_timing: id 2 | task 88260 | n_decoded = 231, tg = 14.39 t/s, tg_3s = 14.43 t/s
206.18.987.716 I slot print_timing: id 2 | task 88260 | n_decoded = 275, tg = 14.39 t/s, tg_3s = 14.37 t/s
206.22.042.189 I slot print_timing: id 2 | task 88260 | n_decoded = 319, tg = 14.39 t/s, tg_3s = 14.41 t/s
206.25.088.065 I slot print_timing: id 2 | task 88260 | n_decoded = 363, tg = 14.40 t/s, tg_3s = 14.45 t/s
206.28.109.298 I slot print_timing: id 2 | task 88260 | n_decoded = 406, tg = 14.38 t/s, tg_3s = 14.23 t/s
206.31.165.836 I slot print_timing: id 2 | task 88260 | n_decoded = 450, tg = 14.38 t/s, tg_3s = 14.40 t/s
206.34.167.608 I slot print_timing: id 2 | task 88260 | n_decoded = 493, tg = 14.38 t/s, tg_3s = 14.32 t/s
206.37.227.147 I slot print_timing: id 2 | task 88260 | n_decoded = 537, tg = 14.38 t/s, tg_3s = 14.38 t/s
206.40.296.965 I slot print_timing: id 2 | task 88260 | n_decoded = 581, tg = 14.37 t/s, tg_3s = 14.33 t/s
206.43.366.251 I slot print_timing: id 2 | task 88260 | n_decoded = 625, tg = 14.37 t/s, tg_3s = 14.34 t/s
206.46.433.415 I slot print_timing: id 2 | task 88260 | n_decoded = 669, tg = 14.37 t/s, tg_3s = 14.35 t/s
206.49.439.363 I slot print_timing: id 2 | task 88260 | n_decoded = 712, tg = 14.36 t/s, tg_3s = 14.31 t/s
206.49.577.558 I slot print_timing: id 2 | task 88260 | prompt eval time = 8380.47 ms / 214 tokens ( 39.16 ms per token, 25.54 tokens per second)
206.49.577.563 I slot print_timing: id 2 | task 88260 | eval time = 49703.25 ms / 714 tokens ( 69.61 ms per token, 14.37 tokens per second)
206.49.577.564 I slot print_timing: id 2 | task 88260 | total time = 58083.72 ms / 928 tokens
206.49.577.566 I slot print_timing: id 2 | task 88260 | graphs reused = 88114
206.49.588.178 I slot release: id 2 | task 88260 | stop processing: n_tokens = 257885, truncated = 0
206.51.269.656 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.999 (> 0.100 thold), f_keep = 1.000
206.51.278.061 I slot launch_slot_: id 2 | task 88976 | processing task, is_child = 0
207.00.848.880 I slot print_timing: id 2 | task 88976 | prompt processing, n_tokens = 353, progress = 1.00, t = 9.57 s / 36.89 tokens per second
207.07.998.873 I slot print_timing: id 2 | task 88976 | n_decoded = 100, tg = 14.53 t/s, tg_3s = 14.53 t/s
207.11.040.566 I slot print_timing: id 2 | task 88976 | n_decoded = 144, tg = 14.51 t/s, tg_3s = 14.47 t/s
207.13.122.810 I slot print_timing: id 2 | task 88976 | prompt eval time = 9835.26 ms / 357 tokens ( 27.55 ms per token, 36.30 tokens per second)
207.13.122.815 I slot print_timing: id 2 | task 88976 | eval time = 12007.15 ms / 174 tokens ( 69.01 ms per token, 14.49 tokens per second)
207.13.122.816 I slot print_timing: id 2 | task 88976 | total time = 21842.41 ms / 531 tokens
207.13.122.817 I slot print_timing: id 2 | task 88976 | graphs reused = 88285
207.13.133.468 I slot release: id 2 | task 88976 | stop processing: n_tokens = 258415, truncated = 0

here is a full logs