From 1b7624bf5cfc105a53a5f3f3f5486711ab15d429 Mon Sep 17 00:00:00 2001
From: Serena <yangsijia.614@bytedance.com>
Date: Thu, 6 Mar 2025 05:28:50 +0800
Subject: [PATCH] [misc] Add FlashMLA as a new option of VLLM_ATTENTION_BACKEND
 env (#14267)

---
 vllm/envs.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/vllm/envs.py b/vllm/envs.py
index f6c038967b698..edabd647db2f7 100644
--- a/vllm/envs.py
+++ b/vllm/envs.py
@@ -321,6 +321,7 @@ environment_variables: dict[str, Callable[[], Any]] = {
     # - "XFORMERS": use XFormers
     # - "ROCM_FLASH": use ROCmFlashAttention
     # - "FLASHINFER": use flashinfer
+    # - "FLASHMLA": use FlashMLA
     "VLLM_ATTENTION_BACKEND":
     lambda: os.getenv("VLLM_ATTENTION_BACKEND", None),