[2/2] Support Qserve (#6521)

2025-05-24 03:39:18 +08:00
parent d2e0881a34
commit 1b2e8f76d9
5 changed files with 268 additions and 5 deletions
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -577,6 +577,7 @@ class ServerArgs:
                "w8a8_int8",
                "w8a8_fp8",
                "moe_wna16",
+                "qoq",
            ],
            help="The quantization method.",
        )