xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-26 23:07:55 +08:00
Code Issues 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
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats 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]: