Skip to content

[BUGFIX][v0.9.1] ep_group is not equal to word_size in some cases. #1862

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Jul 18, 2025
Merged

[BUGFIX][v0.9.1] ep_group is not equal to word_size in some cases. #1862

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
0d9eb4c
[BUGFIX][v0.9.1] fix enable_multistream_moe bug when DBO is enabled (…
Jul 16, 2025
8da5ac1
[BUGFIX][v0.9.1] fix enable_multistream_moe bug when DBO is enabled (…
Jul 16, 2025
9c4903f
[BUGFIX][v0.9.1] fix enable_multistream_moe bug when DBO is enabled (…
Jul 16, 2025
e6cdf86
[BUGFIX][v0.9.1] fix enable_multistream_moe bug when DBO is enabled (…
Jul 16, 2025
6b3b082
[BUGFIX][v0.9.1] fix enable_multistream_moe bug when DBO is enabled (…
Jul 17, 2025
db7887c
[BUGFIX][v0.9.1] fix enable_multistream_moe bug when DBO is enabled (…
Jul 17, 2025
ca62bc0
[BUGFIX][v0.9.1] ep_group is not equal to word_size in some cases.
Jul 18, 2025
dd08fc3
[BUGFIX][v0.9.1] clean code.
Jul 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions vllm_ascend/ascend_forward_context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@

import torch
from vllm.config import VllmConfig
from vllm.distributed import get_dp_group, get_tp_group
from vllm.distributed import get_dp_group, get_ep_group, get_tp_group
from vllm.forward_context import get_forward_context, set_forward_context
from vllm.platforms import current_platform

Expand Down Expand Up @@ -63,7 +63,7 @@ def set_ascend_forward_context(
):
forward_context = get_forward_context()
forward_context.with_prefill = with_prefill
ep_size = (torch.distributed.get_world_size() if
ep_size = (get_ep_group().world_size if
vllm_config.parallel_config.enable_expert_parallel else 1)

fused_moe_state = get_fused_moe_state(ep_size, with_prefill)
Expand Down