Skip to content

[bugfix] fix graph_batch_sizes padding bug #1607

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

Open
wants to merge 1 commit into
base: v0.9.1-dev
Choose a base branch
from
Open

[bugfix] fix graph_batch_sizes padding bug #1607

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion vllm_ascend/worker/model_runner_v1.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2101,7 +2101,8 @@ def check_torchair_graph_batch_sizes(self):
if self.parallel_config.enable_expert_parallel:
new_graph_batch_sizes = []
for graph_batch_size in self.torchair_graph_batch_sizes:
cur_graph_batch_size = graph_batch_size + tp_size - graph_batch_size % tp_size
cur_graph_batch_size = math.ceil(
graph_batch_size / tp_size) * tp_size
if cur_graph_batch_size not in new_graph_batch_sizes:
new_graph_batch_sizes.append(cur_graph_batch_size)
self.torchair_graph_batch_sizes = new_graph_batch_sizes