[Bugfix] Disable gptq_bitblas for <SM80 to fix GPTQ on V100/T4 (#17541)

Signed-off-by: mgoin <mgoin64@gmail.com>
2025-05-01 18:59:35 -06:00
parent 39c0813a7f
commit 24aebae177
1 changed files with 1 additions and 1 deletions
--- a/vllm/model_executor/layers/quantization/gptq_bitblas.py
+++ b/vllm/model_executor/layers/quantization/gptq_bitblas.py
@@ -134,7 +134,7 @@ class GPTQBitBLASConfig(QuantizationConfig):

    @classmethod
    def get_min_capability(cls) -> int:
-        return 70
+        return 80

    @classmethod
    def get_config_filenames(cls) -> List[str]: