Support mxfp4 for GPT-OSS (#8843)

Co-authored-by: Co-author fzyzcjy <ch271828n@outlook.com>
Co-authored-by: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com>
Co-authored-by: zhuofan1123 <zhuofanl@nvidia.com>
Co-authored-by: liz-badada <jinyanc@nvidia.com>
Co-authored-by: xutizhou <xutingz@nvidia.com>
Co-authored-by: linhu-nv <linhu@nvidia.com>

python/sglang/srt/layers/quantization/unquant.py

@@ -272,6 +272,8 @@ class UnquantizedFusedMoEMethod(FusedMoEMethodBase, CustomOp):
                     activation=activation,
                     activation_alpha=activation_alpha,
                     swiglu_limit=swiglu_limit,
+                    w1_pcg=None,
+                    w2_pcg=None,
                 )
             else:
                 return self.triton_kernel_moe_forward(