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

Fix some typing issues found by mypy==1.18.2 (#26596)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-10 19:21:25 +01:00
committed by GitHub
parent 3b780a4bbb
commit 7c12763b24
6 changed files with 19 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/model_loader/bitsandbytes_loader.py
View File

@@ -542,8 +542,7 @@ class BitsAndBytesModelLoader(BaseModelLoader):
)
quant_config = getattr(model_config.hf_config, "quantization_config", None)
if quant_config is not None:
quant_method = quant_config.get("quant_method")
if quant_config and (quant_method := quant_config.get("quant_method")):
if quant_method == "bitsandbytes":
self.pre_quant = True
else:
@@ -558,7 +557,7 @@ class BitsAndBytesModelLoader(BaseModelLoader):
"Prequant BitsAndBytes models with tensor parallelism is not "
"supported. Please try with pipeline parallelism."
)
if self.pre_quant:
if quant_config and self.pre_quant:
self.load_8bit = quant_config.get("load_in_8bit", False)
def _initialize_loader_state(