xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-12 06:37:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
Bill Nell 2025-05-28 23:19:49 +00:00
parent c169b05541
commit cad6447664
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/layers/fused_moe/layer.py
View File

@ -274,6 +274,7 @@ class FusedMoEMethodBase(QuantizeMethodBase):
handle = all2all_manager.get_handle(all_to_all_args)
logger.debug("PplxPrepareAndFinalize")
prepare_finalize = PplxPrepareAndFinalize(
handle,
max_num_tokens=moe.max_num_tokens,