Support OCP MXFP4 quantization on AMD GPUs (#8255)

Co-authored-by: wunhuang <wunhuang@amd.com> Co-authored-by: Hubert Lu <Hubert.Lu@amd.com>
2025-08-05 09:14:52 +08:00
parent 7cb20754fa
commit d4bf5a8524
12 changed files with 1159 additions and 1 deletions
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -813,6 +813,7 @@ class ServerArgs:
                "moe_wna16",
                "qoq",
                "w4afp8",
+                "mxfp4",
            ],
            help="The quantization method.",
        )