xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 20:45:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V1] TPU - Fix fused MOE (#15834)

Browse Source 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
This commit is contained in:
Alexander Matveev 2025-04-01 01:58:07 -04:00 committed by GitHub
parent 63d8eabed0
commit 7e4e709b43
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/fused_moe/layer.py
View File

@ -309,7 +309,7 @@ class UnquantizedFusedMoEMethod(FusedMoEMethodBase, CustomOp):
expert_map=expert_map, expert_map=expert_map,
renormalize=renormalize) renormalize=renormalize)
forward_native = forward_cuda forward_native = forward_tpu if current_platform.is_tpu else forward_cuda
def determine_expert_map( def determine_expert_map(