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>

python/sglang/srt/configs/model_config.py

@@ -391,6 +391,7 @@ class ModelConfig:
             "compressed-tensors",
             "fbgemm_fp8",
             "w8a8_fp8",
+            "petit_nvfp4",
         ]
         optimized_quantization_methods = [
             "fp8",
@@ -408,9 +409,11 @@ class ModelConfig:
             "moe_wna16",
             "qoq",
             "w4afp8",
+            "petit_nvfp4",
         ]
         compatible_quantization_methods = {
             "modelopt_fp4": ["modelopt"],
+            "petit_nvfp4": ["modelopt"],
             "w8a8_int8": ["compressed-tensors", "compressed_tensors"],
             "w8a8_fp8": ["compressed-tensors", "compressed_tensors"],
         }