From 89fca671fbb579d0840818afaece575c71b0b892 Mon Sep 17 00:00:00 2001 From: Simon Mo Date: Mon, 17 Mar 2025 06:54:40 -0700 Subject: [PATCH] [V1] Default MLA to V1 (#14921) Signed-off-by: simon-mo --- vllm/engine/arg_utils.py | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/vllm/engine/arg_utils.py b/vllm/engine/arg_utils.py index 4e695da4ef765..49b8b0d5ca13d 100644 --- a/vllm/engine/arg_utils.py +++ b/vllm/engine/arg_utils.py @@ -1191,7 +1191,7 @@ class EngineArgs: NOTE: for autoselection of V0 vs V1 engine, we need to create the ModelConfig first, since ModelConfig's attrs (e.g. the model arch) are needed to make the decision. - + This function set VLLM_USE_V1=X if VLLM_USE_V1 is unspecified by the user. @@ -1576,10 +1576,6 @@ class EngineArgs: ############################################################# # Experimental Features - allow users to opt in. - # MLA is is supported on V1, but off by default for now. - if model_config.use_mla and _warn_or_fallback("MLA"): - return False - # LoRA is supported on V1, but off by default for now. if self.enable_lora and _warn_or_fallback("LORA"): return False