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

Move verify_marlin_supported to GPTQMarlinLinearMethod (#8165)

Browse Source
This commit is contained in:
Michael Goin 2024-09-05 11:09:46 -04:00 committed by GitHub
parent 9da25a88aa
commit 2ee45281a5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/model_executor/layers/quantization/gptq_marlin.py
View File

@ -51,10 +51,6 @@ class GPTQMarlinConfig(QuantizationConfig):
self.quant_type = self.TYPE_MAP[(weight_bits, is_sym)]
# Verify supported on platform.
verify_marlin_supported(quant_type=self.quant_type,
group_size=self.group_size)
def __repr__(self) -> str:
return (f"GPTQMarlinConfig(quant_type={self.quant_type}, "
f"group_size={self.group_size}, "
@ -153,6 +149,10 @@ class GPTQMarlinLinearMethod(LinearMethodBase):
def __init__(self, quant_config: GPTQMarlinConfig) -> None:
self.quant_config = quant_config
# Verify supported on platform.
verify_marlin_supported(quant_type=self.quant_config.quant_type,
group_size=self.quant_config.group_size)
def create_weights(
self,
layer: torch.nn.Module,