sunjichen/enginex-c_series-vllm
1
0
Fork 0
forked from EngineX-MetaX/enginex-c_series-vllm
Code Pull Requests Activity
Files
ce688181e68c103c2b10d20ef51f5f7c9e42cd93
enginex-c_series-vllm/README.md

326 B
Raw Blame History

metax-c500-vllm

  1. 支持 gpt-oss：将 vllm 目录覆盖到镜像中的 /opt/conda/lib/python3.10/site-packages/vllm。运行gpt-oss时需指定VLLM_ATTENTION_BACKEND=TRITON_ATTN_VLLM_V1
  2. 将 code_generator.py 覆盖到镜像中的 /opt/conda/lib/python3.10/site-packages/triton/compiler/code_generator.py