xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 15:25:48 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Slight improvement of the BNB (#19418)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Jee Jee Li 2025-06-10 21:51:49 +08:00 committed by GitHub
parent 64a9af5afa
commit b6553be1bc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/layers/quantization/bitsandbytes.py
View File

@ -71,9 +71,7 @@ class BitsAndBytesConfig(QuantizationConfig):
@staticmethod
def get_config_filenames() -> list[str]:
return [
"adapter_config.json",
]
return []
@classmethod
def from_config(cls, config: dict[str, Any]) -> "BitsAndBytesConfig":

3
vllm/model_executor/model_loader/bitsandbytes_loader.py
View File

@ -392,7 +392,8 @@ class BitsAndBytesModelLoader(BaseModelLoader):
def _get_bnb_target_modules(self, model: nn.Module) -> None:
for name, module in model.named_modules():
if isinstance(module, (LinearBase, )):
if (isinstance(module, LinearBase) and
hasattr(module.quant_method, "quant_config")):
if modules_info := self.modules_mapping.get_sub_modules(name):
# Map vllm's names to transformers's names.
rep_name, sub_modules = modules_info