Enable native ModelOpt quantization support (1/3) (#7149)

Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
2025-10-06 13:24:15 -07:00
parent eb30b888db
commit 155cbb51f0
11 changed files with 464 additions and 42 deletions
--- a/python/sglang/srt/layers/quantization/modelopt_quant.py
+++ b/python/sglang/srt/layers/quantization/modelopt_quant.py
@@ -113,7 +113,7 @@ class ModelOptFp8Config(QuantizationConfig):

    @classmethod
    def get_name(cls) -> str:
-        return "modelopt"
+        return "modelopt_fp8"

    @classmethod
    def get_supported_act_dtypes(cls) -> List[torch.dtype]: