diff --git a/vllm/model_executor/layers/batch_invariant.py b/vllm/model_executor/layers/batch_invariant.py
index bec7af0286345..8b33727f05fbc 100644
--- a/vllm/model_executor/layers/batch_invariant.py
+++ b/vllm/model_executor/layers/batch_invariant.py
@@ -805,11 +805,11 @@ def override_envs_for_invariance():
         "FLASH_ATTN",  # best supported backend
         "FLASHINFER",
         "FLASH_ATTN_MLA",
-        "TRITON_MLA",
         # Not yet supported MLA backends
         # "FLASHMLA",
         # "FLEX_ATTENTION", # IMA issue even if we disable batch invariance
         # "FLASHINFER_MLA", https://github.com/vllm-project/vllm/pull/28967
+        # "TRITON_MLA",
     ]
     if curr_attn_backend not in supported_backends:
         warning = (