EngineX-MetaX/enginex-c_series-vllm
8
1
Fork 1
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[gpt-oss] Add gpt-oss mxfp4 support

Browse Source
This commit is contained in:
wangjing
2025-08-25 15:31:09 +08:00
parent db7f48eeac
commit 7a35b2f32d
32 changed files with 4835 additions and 1190 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -1,4 +1,6 @@
# metax-c500-vllm
1. 支持 `gpt-oss-BF16`：将 `vllm` 目录覆盖到镜像中的 `/opt/conda/lib/python3.10/site-packages/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`
*此版本改动较大，可能因为接口改动，存在部分模型运行出错的问题。*