search

mlcommons / inference_policies

Issues related to MLPerf™ Inference policies, including rules and suggested changes
https://mlcommons.org/en/groups/inference/
Apache License 2.0
55 stars 52 forks source link

Add Mixtral-8x7B rules #295

Closed pgmpablo157321 closed 2 months ago

github-actions[bot] commented 2 months ago

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

rnaidu02 commented 2 months ago

Max input token length should be 2048 as per meeting notes. The PR lists max_seq_len=1024. @pgmpablo157321 Can you double check?