Skip to content

[BugFix][Minor] Fix full cuda graph bug when max_num_seqs < 512 #19171

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 3 commits into from
Jun 5, 2025
Merged

[BugFix][Minor] Fix full cuda graph bug when max_num_seqs < 512 #19171

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e94a3f4
[BugFix] Fix full cuda graph bug when max_num_seqs < 512
WoosukKwon Jun 5, 2025
ca84974
minor
WoosukKwon Jun 5, 2025
9c7c87a
minor
WoosukKwon Jun 5, 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/v1/worker/gpu_model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1737,7 +1737,7 @@ def _dummy_run(
# has num_tokens in total.
assert num_tokens <= self.scheduler_config.max_num_batched_tokens
max_num_reqs = self.scheduler_config.max_num_seqs
num_reqs = max_num_reqs if num_tokens >= max_num_reqs else num_tokens
num_reqs = min(num_tokens, max_num_reqs)
min_tokens_per_req = num_tokens // num_reqs
num_scheduled_tokens_list = [min_tokens_per_req] * num_reqs
num_scheduled_tokens_list[-1] += num_tokens % num_reqs
Expand Down Expand Up @@ -1765,7 +1765,7 @@ def _dummy_run(
self.kv_cache_config.kv_cache_groups):
attn_metadata_i = (
self.attn_metadata_builders[kv_cache_group_id].build(
num_reqs=num_tokens,
num_reqs=num_reqs,
num_actual_tokens=num_tokens,
max_query_len=num_tokens,
common_prefix_len=0,
Expand Down