lm-sys/FastChat

Issues with VLLM Integration Speedup

オープン

#2,362 opened on 2023/09/05

 (4 件のコメント) (0 件のリアクション) (0 人の担当者)Python (4,736 件のフォーク)batch import
good first issue

Repository metrics

Stars
 (38,959 個のスター)
PR merge metrics
 (PR metrics pending)

説明

Hello,

I've been trying to work with the [vLLM integration] and I'm facing some performance discrepancies. According to the documentation, I should achieve a significant speedup, but in my tests, I'm seeing different results:

Directly running with FastChat: 16 t/s Using the VLLM integration: 25 t/s (only 1.5x speedup) VLLM offline inference: 90 t/s (expected 6x speedup) I'm running Vicuna33b on a gin H100 gpu. Has anyone experienced this before? Are there any additional configurations or tweaks I might be missing to get the desired speedup?

Thanks in advance for any guidance or advice!

コントリビューターガイド