# Can't change max\_input\_length of Text Generation Inference

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcant-change-max-input-length-of-text-generation-inference%2F86925%3E%5C
**Category:** Intermediate\
**Created:** [May 15, 2024, 11:46pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcant-change-max-input-length-of-text-generation-inference%2F86925 "2024-05-15T23:46:15Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![narai](https://avatars.discourse-cdn.com/v4/letter/n/94ad74/32.png) [@narai](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnarai)%5C
**Post date:** [May 15, 2024, 11:46pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcant-change-max-input-length-of-text-generation-inference%2F86925%2F1 "2024-05-15T23:46:15Z")

</div>

It appears that the TGI CLI options can be passed to the docker command in the TGI docker launch script (for example this works for --model-id and --max-total-tokens and --quantize). However, when I try to specify --max-input-tokens, I get this error:

error: unexpected argument ‘–max-input-tokens’ found