Skip to content

[V1][BugFix] Fix for mixed top_k batch #14301

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 1 commit into from
Mar 5, 2025
Merged

[V1][BugFix] Fix for mixed top_k batch #14301

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
7 changes: 5 additions & 2 deletions vllm/v1/worker/gpu_input_batch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -264,9 +264,12 @@ def add_request(
self.top_p_cpu[req_index] = sampling_params.top_p
if sampling_params.top_p < 1:
self.top_p_reqs.add(req_id)
self.top_k_cpu[req_index] = sampling_params.top_k
if sampling_params.top_k > 0:
top_k = sampling_params.top_k
if 0 < top_k < self.vocab_size:
self.top_k_reqs.add(req_id)
else:
top_k = self.vocab_size
self.top_k_cpu[req_index] = top_k
self.min_p_cpu[req_index] = sampling_params.min_p
self.frequency_penalties_cpu[
req_index] = sampling_params.frequency_penalty
Expand Down