[Misc] Update to comply with the new compressed-tensors config (#5350)

Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-06-09 23:49:46 -04:00
parent 45f92c00cf
commit 5884c2b454
4 changed files with 19 additions and 20 deletions
--- a/vllm/model_executor/layers/quantization/init.py
+++ b/vllm/model_executor/layers/quantization/init.py
@@ -31,7 +31,7 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
    "gptq_marlin": GPTQMarlinConfig,
    "gptq": GPTQConfig,
    "squeezellm": SqueezeLLMConfig,
-    "sparseml": CompressedTensorsConfig,
+    "compressed-tensors": CompressedTensorsConfig,
    "bitsandbytes": BitsAndBytesConfig,
 }