@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / fbdb7b3ee2
Fork 0

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 17, 00:30 UTC

[Core] Allow AQLM on Pascal (#5058)

sasha0552 committed May 27, 2024 at 22:26 UTC fbdb7b3ee2c3f7b58841c12b52ed4c83f508babb
1 file changed +1 -1
vllm/model_executor/layers/quantization/aqlm.py
+1 -1
@@ -192,7 +192,7 @@ class AQLMConfig(QuantizationConfig):
192
193 @classmethod
194 def get_min_capability(cls) -> int:
195 - return 70
195 + return 60
196
197 @classmethod
198 def get_config_filenames(cls) -> List[str]: