xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-06 00:07:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix use_ep

Browse Source 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Tyler Michael Smith 2025-04-07 19:56:41 +00:00
parent 090c856d76
commit 87e47eb1db
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

@ -437,7 +437,7 @@ class FusedMoE(torch.nn.Module):
# Use expert parallelism instead of tensor parallelism?
vllm_config = get_current_vllm_config()
use_ep = (vllm_config.parallel_config.enable_expert_parallel
and self.tp_size > 1)
and (self.tp_size != 1 or self.dp_size != 1))
# For smuggling this layer into the fused moe custom op
self.use_direct_call = self.dp_size == 1