neuralmagic / nm-vllm

A high-throughput and memory-efficient inference and serving engine for LLMs
https://nm-vllm.readthedocs.io
Other
251 stars 10 forks source link

remove loop short circuit #372

Closed andy-neuma closed 4 months ago

andy-neuma commented 4 months ago

SUMMARY:

TEST PLAN: runs on remote push

andy-neuma commented 4 months ago

cancelled run after seeing that the "benchmark" was green.