Remove unused use_marlin variable in Mxfp4MoEMethod (#31549)

Signed-off-by: vaibhav sourirajan <vs2787@columbia.edu>
2026-01-02 00:13:36 -05:00
parent ca179d0f64
commit 1f43c121d5
1 changed files with 0 additions and 1 deletions
--- a/vllm/model_executor/layers/quantization/mxfp4.py
+++ b/vllm/model_executor/layers/quantization/mxfp4.py
@@ -240,7 +240,6 @@ class Mxfp4MoEMethod(FusedMoEMethodBase):
        self.mxfp4_backend = get_mxfp4_backend(moe.is_lora_enabled)

        self.marlin_input_dtype = None
-        self.use_marlin = self.mxfp4_backend == Mxfp4Backend.MARLIN
        self.max_capture_size = (
            get_current_vllm_config().compilation_config.max_cudagraph_capture_size
        )