RedHatAI/quantization
Updated • 7
Edit Models filters
Model Tree
Apps
Inference Providers
One-click Deployment
Models
84
Active filters: kernel
RedHatAI/moe
Updated • 3
medmekk/LlamaRMSNorm-triton
Updated
medmekk/rmsnorm
Updated
medmekk/triton-llama-mlp
Updated
medmekk/triton-llama-attn
Updated
cdreetz/kwen2.5-1.5b
Text Generation • 2B • Updated • 35
EricB/kernels-paged-attention-metal
Updated • 1
drbh/img2gray
Updated • 4
cdreetz/kwen2.5-1.5b-v2
Text Generation • 2B • Updated • 39
medmekk/triton-flash-attn-sink-clone
Updated • 1
JinnP/Qwen3-8B-Kernelbook-SFT-HF
Text Generation • 8B • Updated • 17 • 1
mradermacher/Qwen3-8B-Kernelbook-SFT-HF-GGUF
8B • Updated • 231 • 1
drbh/yamoe
Updated • 3
gagan3012/batch_invariant_kernel
Updated • 3
shisa-ai/megablocks-hip
Updated • 1
AhmedAyman/k2-think-cuda-1505
Text Generation • Updated • 11
logos-flux/gb10-rmsnorm
Updated • 3
AbstractPhil/svd-triton
Updated
DuoNeural/AdQWENistrator-9B
Text Generation • 9B • Updated • 20 • 4
DuoNeural/AdQWENistrator-9B-GGUF
Text Generation • 9B • Updated • 58 • 1
mradermacher/AdQWENistrator-9B-GGUF
9B • Updated • 523 • 1
mradermacher/AdQWENistrator-9B-i1-GGUF
9B • Updated • 1.31k • 2
Entrit/tritllm-kernel
Updated
Frosty40/hydra
Updated
odyssey-systems/dropout-layer-norm
Updated
odyssey-systems/fused-dense-lib
Updated
Deep-ML/flash-attention-in-cuda-from-scratch
Updated
transformerlab/ideogram-4-int8-fused
Text-to-Image • Updated • 2
Momin-Aldahdouh/MominoMoE-v2
Text Generation • 0.6B • Updated • 38