From 971932d66117af03f5a4833d5fdf1ee42fba2c79 Mon Sep 17 00:00:00 2001
From: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Date: Fri, 7 Aug 2026 04:54:25 +0800
Subject: [PATCH] [Kimi-K3] Allow DSPARK verify on cutedsl_mla (fold_sq)
 (#33650)

---
 python/sglang/srt/arg_groups/overrides.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/python/sglang/srt/arg_groups/overrides.py b/python/sglang/srt/arg_groups/overrides.py
index f5af1ddbc..7ef959181 100644
--- a/python/sglang/srt/arg_groups/overrides.py
+++ b/python/sglang/srt/arg_groups/overrides.py
@@ -362,8 +362,10 @@ def _dspark_verify_on_decode_backend(
     if backend == "tokenspeed_mla":
         return kv_cache_dtype == "fp8_e4m3" and q_len <= 8
     if backend == "cutedsl_mla":
-        # The cute-dsl kernel rejects q_len >= 5 with no fallback.
-        return q_len <= 4
+        # cute-dsl monolithic MLA decode folds the verify tokens into the head
+        # dim (fold_sq), so it serves any DSPARK verify width. Needs flashinfer
+        # >= 0.6.15 (older builds reject q_len >= 5).
+        return True
     return False