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]: