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

[Quantization] enable compressed-tensors marlin support for turing (#31000)

Browse Source 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
This commit is contained in:
Jinzhen Lin
2025-12-19 12:29:48 +08:00
committed by GitHub
parent 2ac85a4544
commit de08b8f61b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py
View File

@@ -30,7 +30,7 @@ from .MPLinearKernel import MPLinearKernel, MPLinearLayerConfig
class MarlinLinearKernel(MPLinearKernel): class MarlinLinearKernel(MPLinearKernel):
@classmethod @classmethod
def get_min_capability(cls) -> int: def get_min_capability(cls) -> int:
return 80 return 75
@classmethod @classmethod
def can_implement(cls, c: MPLinearLayerConfig) -> tuple[bool, str | None]: def can_implement(cls, c: MPLinearLayerConfig) -> tuple[bool, str | None]: