Add KV4-capable backend flashmla and update server args (#14989)

Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
2025-12-12 11:50:27 -08:00
parent 4b7b5af36a
commit 171b442ad3
2 changed files with 2 additions and 1 deletions
--- a/python/sglang/srt/server_args.py
+++ b/python/sglang/srt/server_args.py
@@ -1607,6 +1607,7 @@ class ServerArgs:
                            "cutlass_mla",
                            "flashinfer",
                            "trtllm_mla",
+                            "flashmla",
                        ]
                        assert (
                            self.attention_backend in KV4_ATTENTION_MLA_BACKEND_CHOICES