wanglin/enginex-vllm-bi100-qwen36
1
1
Fork 0
forked from EngineX-Iluvatar/enginex-vllm-bi100-qwen36
Code Pull Requests Activity

add --hf-overrides architectures=Qwen3_5MoeForCausalLM (fix model config arch mismatch)

Browse Source
This commit is contained in:
wanglin
2026-10-02 20:00:19 +08:00
parent 941c42a04f
commit ee1c3c4c9b
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
computility-run.yaml
View File

@@ -30,6 +30,8 @@ command:
- --reasoning-parser
- qwen3
- --enable-prefix-caching
- --hf-overrides
- '{"architectures":["Qwen3_5MoeForCausalLM"]}'
- --dtype
- half
env: