From 0d116b9a0b0a1dade0b60e3825385c7aae781ee9 Mon Sep 17 00:00:00 2001
From: Vincent Zhong <207368749+vincentzed@users.noreply.github.com>
Date: Sat, 15 Nov 2025 11:50:15 -0500
Subject: [PATCH] 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  | 1 -
 python/sglang/srt/layers/quantization/fp8.py            | 1 -
 python/sglang/srt/layers/quantization/modelopt_quant.py | 1 -
 python/sglang/srt/layers/quantization/mxfp4.py          | 1 -
 4 files changed, 4 deletions(-)

diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/layer.py b/python/sglang/srt/layers/moe/fused_moe_triton/layer.py
index bc5129a97..1aadc61fe 100644
--- 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 @@ 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,
diff --git a/python/sglang/srt/layers/quantization/fp8.py b/python/sglang/srt/layers/quantization/fp8.py
index 7b4870c97..425d4f97f 100644
--- a/python/sglang/srt/layers/quantization/fp8.py
+++ b/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,
             )
diff --git a/python/sglang/srt/layers/quantization/modelopt_quant.py b/python/sglang/srt/layers/quantization/modelopt_quant.py
index 99ae27684..f3f7b85ea 100755
--- a/python/sglang/srt/layers/quantization/modelopt_quant.py
+++ b/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,
                 )
 
diff --git a/python/sglang/srt/layers/quantization/mxfp4.py b/python/sglang/srt/layers/quantization/mxfp4.py
index 847eaf0ee..137cdb683 100644
--- a/python/sglang/srt/layers/quantization/mxfp4.py
+++ b/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,