FP4 weight loading and inference (2/2) (#3972)

2025-04-08 17:26:21 -07:00
parent 5039d54772
commit 11d760d56a
6 changed files with 262 additions and 1 deletions
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -495,6 +495,7 @@ class ServerArgs:
                "bitsandbytes",
                "gguf",
                "modelopt",
+                "modelopt_fp4",
                "w8a8_int8",
                "w8a8_fp8",
                "moe_wna16",