Fix/resupport nongated fused moe triton (#36412)

Signed-off-by: Shaun Kotek - Nvidia <skotek@nvidia.com>
Signed-off-by: Natan Bagrov <nbagrov@nvidia.com>
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Signed-off-by: liweiguang <codingpunk@gmail.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Alex Brooks <albrooks@redhat.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: cong-or <conchubhar.gannon@gmail.com>
Signed-off-by: Tushar Shetty <tushar.shetty@abbyy.com>
Signed-off-by: Tushar Shetty <54362365+tusharshetty61@users.noreply.github.com>
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
Signed-off-by: Xin Yang <xyangx@amazon.com>
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: nvnbagrov <nbagrov@nvidia.com>
Co-authored-by: Sage <80211083+sagearc@users.noreply.github.com>
Co-authored-by: danisereb <daserebrenik@nvidia.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Weiguang Li <codingpunk@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: cong-or <conchubhar.gannon@gmail.com>
Co-authored-by: Tushar Shetty <54362365+tusharshetty61@users.noreply.github.com>
Co-authored-by: liuzhenwei <zhenwei.liu@intel.com>
Co-authored-by: Xin Yang <105740670+xyang16@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

vllm/model_executor/layers/fused_moe/fused_batched_moe.py

@@ -912,7 +912,7 @@ class BatchedTritonExperts(mk.FusedMoEExpertsModular):
 
     @staticmethod
     def _supports_no_act_and_mul() -> bool:
-        return False
+        return True
 
     @staticmethod
     def _supports_quant_scheme(

vllm/model_executor/layers/fused_moe/fused_moe.py

@@ -1944,7 +1944,7 @@ class TritonExperts(mk.FusedMoEExpertsModular):
 
     @staticmethod
     def _supports_no_act_and_mul() -> bool:
-        return False
+        return True
 
     @staticmethod
     def _supports_quant_scheme(
@@ -1983,6 +1983,9 @@ class TritonExperts(mk.FusedMoEExpertsModular):
             MoEActivation.GELU,
             MoEActivation.SWIGLUOAI,
             MoEActivation.SWIGLUSTEP,
+            MoEActivation.SILU_NO_MUL,
+            MoEActivation.GELU_NO_MUL,
+            MoEActivation.RELU2_NO_MUL,
         ]
 
     @staticmethod