[Quantization] Enable compressed-tensors AWQ for Turing GPU (#29732)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
Isotr0py
2025-11-30 06:04:28 +00:00
committed by GitHub
parent a491b0911b
commit e1464c3a08
@@ -79,8 +79,8 @@ class CompressedTensorsWNA16(CompressedTensorsScheme):
@classmethod
def get_min_capability(cls) -> int:
# ampere and up
return 80
# Turing and up
return 75
def create_weights(
self,