20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] fix use-ep bug to enable ep by dp/tp size > 1 (#16161)

Browse Source
This commit is contained in:
zxfan-cpu 2025-04-08 11:48:47 +08:00 committed by GitHub
parent f2ebb6f541
commit ad971af8c7
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

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