A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 12, 07:15 UTC
[Quantization] Enable compressed-tensors AWQ for Turing GPU (#29732)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Isotr0py committed
Nov 30, 2025 at 14:04 UTC
e1464c3a0861384974dd6cfa35f2d6ff729ab29c
1 file changed
+2
-2
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py
+2
-2
@@ -79,8 +79,8 @@ class CompressedTensorsWNA16(CompressedTensorsScheme):
79
80
@classmethod
81
def get_min_capability(cls) -> int:
82
- # ampere and up
83
- return 80
82
+ # Turing and up
83
+ return 75
84
85
def create_weights(
86
self,