diff --git a/python/sglang/srt/server_args.py b/python/sglang/srt/server_args.py
index 561fcb88d..9f1e54fc8 100644
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -1664,12 +1664,18 @@ class ServerArgs:
                 (user_set_prefill and self.nsa_prefill_backend != "trtllm")
                 or (user_set_decode and self.nsa_decode_backend != "trtllm")
             )
-            if self.dp_size == 1 and major >= 10 and not user_wants_flashmla:
-                # Default to trtllm on Blackwell without DP attention. The "no DP
-                # attention" limitation does NOT apply to context-parallel prefill
-                # (flashmla_sparse pads heads 64->128 and works under CP), which is
-                # why an explicit flashmla choice above takes this out of the trtllm
-                # branch entirely.
+            if (
+                self.dp_size == 1
+                and major >= 10
+                and not user_wants_flashmla
+                and not self.enable_nsa_prefill_context_parallel
+            ):
+                # Default to trtllm on Blackwell without DP attention. NSA-prefill
+                # context parallelism is excluded here on purpose: the trtllm NSA
+                # prefill path mis-shards k_rope under CP (the rope input carries all
+                # CP ranks' tokens, nnz*cp, but the per-rank rope kernel asserts
+                # k_rope_in.size(0)==nnz). flashmla_sparse pads heads 64->128 and works
+                # under CP, so CP falls through to the flashmla branch below.
                 if not user_set_prefill:
                     self.nsa_prefill_backend = "trtllm"
                 if not user_set_decode: