Clean up deprecated tile_tokens_dim for next flashinfer (#13341)

Signed-off-by: Vincent Zhong <207368749+vincentzed@users.noreply.github.com>

python/sglang/srt/layers/moe/fused_moe_triton/layer.py

@@ -1129,7 +1129,6 @@ class FlashInferFP4MoE(FusedMoE):
             local_expert_offset=self.moe_ep_rank * self.num_local_experts,
             local_num_experts=self.num_local_experts,
             routed_scaling_factor=self.moe_runner_config.routed_scaling_factor,
-            tile_tokens_dim=None,
             routing_method_type=RoutingMethodType.DeepSeekV3,
             do_finalize=True,
             output=symm_output,

python/sglang/srt/layers/quantization/fp8.py

@@ -1245,7 +1245,6 @@ class Fp8MoEMethod(FusedMoEMethodBase):
                 routed_scaling_factor=(
                     routed_scaling_factor if routed_scaling_factor is not None else 1.0
                 ),
-                tile_tokens_dim=None,
                 routing_method_type=routing_method_type,
                 use_shuffled_weight=False,
             )

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

@@ -695,7 +695,6 @@ class ModelOptFp8MoEMethod(FusedMoEMethodBase):
                         else 1.0
                     ),
                     use_routing_scales_on_input=use_routing_scales_on_input,
-                    tile_tokens_dim=None,
                     routing_method_type=routing_method_type,
                 )
 

python/sglang/srt/layers/quantization/mxfp4.py

@@ -681,7 +681,6 @@ class Mxfp4MoEMethod(FusedMoEMethodBase):
                 layer.moe_ep_rank * layer.num_local_experts,  # local_expert_offset
                 layer.num_local_experts,  # local num experts
                 None,
-                None,  # tile_tokens_dim
                 1,  # routing_method_type, renormalize
                 True,  # do finalize
                 output=symm_output,