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

[Bugfix] Fix handling of Tensorizer arguments for LoadConfig (#20643)

Browse Source 
Signed-off-by: Sanger Steel <sangersteel@gmail.com>
This commit is contained in:
Sanger Steel
2025-07-09 11:36:37 -04:00
committed by GitHub
parent efe73d0575
commit 4ac9c33f78
4 changed files with 21 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/model_loader/tensorizer_loader.py
View File

@@ -43,7 +43,7 @@ class TensorizerLoader(BaseModelLoader):
else:
validate_config(load_config.model_loader_extra_config)
self.tensorizer_config = TensorizerConfig(
**load_config.model_loader_extra_config)
**load_config.model_loader_extra_config["tensorizer_config"])
def _verify_config(self, model_config: ModelConfig,
parallel_config: ParallelConfig):