Skip to content

GitLab

Unverified Commit 1f43c121 authored by Vaibhav Sourirajan's avatar Vaibhav Sourirajan Committed by GitHub
Browse files

Remove unused `use_marlin` variable in `Mxfp4MoEMethod` (#31549) 


Signed-off-by: default avatarvaibhav sourirajan <vs2787@columbia.edu>
parent ca179d0f
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 1 deletion
vllm/model_executor/layers/quantization/mxfp4.py
View file @ 1f43c121
......@@ -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
)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment