Support NVFP4 quantized dense models on AMD CDNA2/CDNA3 GPUs (#7302)

Co-authored-by: HAI <hixiao@gmail.com> Co-authored-by: Sai Enduri <saimanas.enduri@amd.com>
2025-07-18 19:59:39 -07:00
parent 3964b352c3
commit d918ab7985
7 changed files with 361 additions and 0 deletions
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -766,6 +766,7 @@ class ServerArgs:
                "gguf",
                "modelopt",
                "modelopt_fp4",
+                "petit_nvfp4",
                "w8a8_int8",
                "w8a8_fp8",
                "moe_wna16",