biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix(docs): fix typos in comments and docstrings (#34836)

Browse Source 
Signed-off-by: machov <mv1742@nyu.edu>
This commit is contained in:
Manrique Vargas
2026-02-19 02:17:41 -05:00
committed by GitHub
parent 9681068cf9
commit ad5aa6bd9f
5 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/gpt_oss.py
View File

@@ -586,7 +586,7 @@ class GptOssModel(nn.Module):
parts = name.split(".")
ids = [s for s in parts if s.isdigit()]
# for amd-quark format that each expert is seperated
# for amd-quark format that each expert is separated
# need to extract the parameter name with experts fused.
# example model: amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8
if len(ids) == 2: