Clean up deprecated tile_tokens_dim for next flashinfer (sgl-project#13341)

vincentzed · web-flow · commit 0d116b9a0b0a · 2025-11-16T00:50:15.000+08:00
Signed-off-by: Vincent Zhong &lt;207368749+vincentzed@users.noreply.github.com&gt;
diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/layer.py b/python/sglang/srt/layers/moe/fused_moe_triton/layer.py
@@ -1129,7 +1129,6 @@ def forward(self, hidden_states: torch.Tensor, topk_output: TopKOutput):
             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,
diff --git a/python/sglang/srt/layers/quantization/fp8.py b/python/sglang/srt/layers/quantization/fp8.py
@@ -1245,7 +1245,6 @@ def apply_with_router_logits(
                 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,
             )
diff --git a/python/sglang/srt/layers/quantization/modelopt_quant.py b/python/sglang/srt/layers/quantization/modelopt_quant.py
@@ -695,7 +695,6 @@ def apply(
                         else 1.0
                     ),
                     use_routing_scales_on_input=use_routing_scales_on_input,
-                    tile_tokens_dim=None,
                     routing_method_type=routing_method_type,
                 )
 
diff --git a/python/sglang/srt/layers/quantization/mxfp4.py b/python/sglang/srt/layers/quantization/mxfp4.py
@@ -681,7 +681,6 @@ def apply(
                 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,

Original file line number	Diff line number	Diff line change
`@@ -1245,7 +1245,6 @@ def apply_with_router_logits(`
`1245`	`1245`	`routed_scaling_factor=(`
`1246`	`1246`	`routed_scaling_factor if routed_scaling_factor is not None else 1.0`
`1247`	`1247`	`),`
`1248`		`- tile_tokens_dim=None,`
`1249`	`1248`	`routing_method_type=routing_method_type,`
`1250`	`1249`	`use_shuffled_weight=False,`
`1251`	`1250`	`)`
Original file line number	Diff line number	Diff line change
`@@ -695,7 +695,6 @@ def apply(`
`695`	`695`	`else 1.0`
`696`	`696`	`),`
`697`	`697`	`use_routing_scales_on_input=use_routing_scales_on_input,`
`698`		`- tile_tokens_dim=None,`
`699`	`698`	`routing_method_type=routing_method_type,`
`700`	`699`	`)`
`701`	`700`