Skip to content
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

[Bugfix] Fix KeyError: 1 When Using LoRA adapters #5164

Merged
merged 8 commits into from
Jun 9, 2024
Merged

[Bugfix] Fix KeyError: 1 When Using LoRA adapters #5164

Changes from 3 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
5f0af13
fix: fix conditional removal of lora_int_id in scheduler.py
BlackBird-Coding May 31, 2024
b8a21cc
fix: remove redundant condition for lora_int_id removal in scheduler.py
BlackBird-Coding May 31, 2024
dcde110
chore: fix Line too long (112 > 80)
BlackBird-Coding May 31, 2024
ec1d582
fix: remove redundant condition for lora_int_id removal in scheduler.py
BlackBird-Coding Jun 7, 2024
f8be7fd
reformat: fix lint error
BlackBird-Coding Jun 7, 2024
8830b61
reformat: remove hidden indent
BlackBird-Coding Jun 7, 2024
95b993b
Merge branch 'vllm-project:main' into main
BlackBird-Coding Jun 7, 2024
3c7d8ae
Merge branch 'vllm-project:main' into main
BlackBird-Coding Jun 9, 2024
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
8 changes: 6 additions & 2 deletions vllm/core/scheduler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -421,8 +421,12 @@ def _schedule_running(
num_running_seqs = seq_group.get_max_num_running_seqs()
budget.subtract_num_seqs(seq_group.request_id,
num_running_seqs)
if curr_loras is not None and seq_group.lora_int_id > 0:
curr_loras.remove(seq_group.lora_int_id)
if (
curr_loras is not None
and seq_group.lora_int_id > 0
and seq_group.lora_int_id in curr_loras
):
curr_loras.remove(seq_group.lora_int_id)

if running_queue:
# Preempt the lowest-priority sequence groups.
Expand Down
Loading