Skip to content

GitLab

Unverified Commit ffc0a279 authored by Elvir Crnčević's avatar Elvir Crnčević Committed by GitHub
Browse files

Add back missing DeepEP LL params (#31911) 


Signed-off-by: default avatarElvir Crncevic <elvircrn@gmail.com>
parent 10ef65ed
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py
View file @ ffc0a279
......@@ -295,6 +295,8 @@ class DeepEPLLPrepareAndFinalize(mk.FusedMoEPrepareAndFinalize):
self.max_tokens_per_rank,
num_experts,
use_fp8=self.use_fp8_dispatch,
round_scale=self.use_ue8m0_dispatch,
use_ue8m0=self.use_ue8m0_dispatch,
**(dict(use_nvfp4=True) if use_nvfp4 else dict()),
**(
dict(x_global_scale=qc_a1_gscale_or_scale)
......
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