mirror of
https://github.com/vllm-project/vllm.git
synced 2025-10-20 14:53:52 +08:00
[V1] TPU - Fix fused MOE (#15834)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
This commit is contained in:
committed by
GitHub
parent
63d8eabed0
commit
7e4e709b43
@ -309,7 +309,7 @@ class UnquantizedFusedMoEMethod(FusedMoEMethodBase, CustomOp):
|
||||
expert_map=expert_map,
|
||||
renormalize=renormalize)
|
||||
|
||||
forward_native = forward_cuda
|
||||
forward_native = forward_tpu if current_platform.is_tpu else forward_cuda
|
||||
|
||||
|
||||
def determine_expert_map(
|
||||
|
Reference in New Issue
Block a user