diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/fused_marlin_moe.py b/python/sglang/srt/layers/moe/fused_moe_triton/fused_marlin_moe.py
index 7f76b2616..2d6ced31d 100644
--- a/python/sglang/srt/layers/moe/fused_moe_triton/fused_marlin_moe.py
+++ b/python/sglang/srt/layers/moe/fused_moe_triton/fused_marlin_moe.py
@@ -1,3 +1,4 @@
+import os
 from typing import Optional
 
 import torch
@@ -10,6 +11,7 @@ from sglang.srt.utils import is_cuda
 from sglang.srt.utils.custom_op import register_custom_op
 
 _is_cuda = is_cuda()
+_K3_MARLIN_LOGGED = set()
 
 if _is_cuda:
     from sgl_kernel import moe_sum_reduce
@@ -237,9 +239,27 @@ def fused_marlin_moe(
 
     # M block size selection logic
     # TODO: tune this further for specific models
+    # [k3] Under EP the topk ids are global-routed (most are -1 =
+    # non-local), so M * topk / E_local overestimates the rows per local expert
+    # by ep_size (TP32/EP32, c=50, gamma 2: 150*16/28 = 86 -> block_m 64, the
+    # kernel then runs 64-row MMA tiles for ~2.7 real rows -> compute-bound).
+    # Estimate with the global expert count instead (150*16/896 = 2.7 -> 8).
+    # SGLANG_MARLIN_EP_BLOCK=0 restores the stock choice; =8/16/32/48/64 forces.
+    _tok_per_expert = M * topk / E
+    _ep_block = os.environ.get("SGLANG_MARLIN_EP_BLOCK", "1")
+    if expert_map is not None and global_num_experts > E and _ep_block == "1":
+        _tok_per_expert = M * topk / global_num_experts
     for block_size_m in [8, 16, 32, 48, 64]:
-        if M * topk / E / block_size_m < 0.9:
+        if _tok_per_expert / block_size_m < 0.9:
             break
+    if _ep_block in ("8", "16", "32", "48", "64"):
+        block_size_m = int(_ep_block)
+    if expert_map is not None and M > 1 and (M, block_size_m) not in _K3_MARLIN_LOGGED and len(_K3_MARLIN_LOGGED) < 8:
+        _K3_MARLIN_LOGGED.add((M, block_size_m))
+        import logging as _lg
+        _lg.getLogger(__name__).info(
+            "[k3] marlin EP block_m=%d (M=%d topk=%d E_local=%d E_global=%d mode=%s)",
+            block_size_m, M, topk, E, global_num_experts, _ep_block)
 
     if global_num_experts == -1:
         global_num_experts = E