Upstream Llama4 Support to Main (#16113)

Signed-off-by: Aston Zhang <22279212+astonzhang@users.noreply.github.com>
Signed-off-by: Chris Thi <chris.c.thi@gmail.com>
Signed-off-by: drisspg <drisspguessous@gmail.com>
Signed-off-by: Jon Swenson <jmswen@gmail.com>
Signed-off-by: Keyun Tong <tongkeyun@gmail.com>
Signed-off-by: Lu Fang <fanglu@meta.com>
Signed-off-by: Xiaodong Wang <xdwang@meta.com>
Signed-off-by: Yang Chen <yangche@fb.com>
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
Signed-off-by: Lu Fang <lufang@fb.com>
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Lucia Fang <fanglu@fb.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/model_executor/layers/quantization/awq_marlin.py

@@ -469,6 +469,7 @@ class AWQMoEMethod(FusedMoEMethodBase):
         custom_routing_function: Optional[Callable] = None,
         scoring_func: str = "softmax",
         e_score_correction_bias: Optional[torch.Tensor] = None,
+        apply_router_weight_on_input: bool = False,
         activation: str = "silu",
     ) -> torch.Tensor:
         assert activation == "silu", "Only SiLU activation is supported."
@@ -476,6 +477,10 @@ class AWQMoEMethod(FusedMoEMethodBase):
             raise NotImplementedError(
                 "Expert Parallelism is not supported for "
                 "fused Marlin MoE method.")
+        if apply_router_weight_on_input:
+            raise NotImplementedError(
+                "Apply router weight on input is not supported for"
+                "fused Marlin MoE method.")
 
         topk_weights, topk_ids = FusedMoE.select_experts(
             hidden_states=x,