Add support for AutoRound quantized models (#10153)

2025-10-27 18:17:29 +08:00
parent a88b006ecf
commit caa4819bfc
8 changed files with 541 additions and 1 deletions
--- a/python/sglang/srt/configs/model_config.py
+++ b/python/sglang/srt/configs/model_config.py
@@ -613,6 +613,7 @@ class ModelConfig:
            "petit_nvfp4",
            "quark",
            "mxfp4",
+            "auto-round",
        ]
        optimized_quantization_methods = [
            "fp8",