squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Core] Fix scheduler considering "no LoRA" as "LoRA" (#4897)

Browse Source
This commit is contained in:
Antoni Baum 2024-05-20 17:48:32 -07:00 committed by GitHub
parent c3af44722c
commit 65ae8c2c8f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/core/scheduler.py
View File

@ -744,8 +744,8 @@ class Scheduler:
budget.add_num_seqs(seq_group.request_id, budget.add_num_seqs(seq_group.request_id,
seq_group.get_max_num_running_seqs()) seq_group.get_max_num_running_seqs())
curr_loras = set( curr_loras = set(
seq_group.lora_int_id seq_group.lora_int_id for seq_group in self.running
for seq_group in self.running) if self.lora_enabled else None if seq_group.lora_int_id > 0) if self.lora_enabled else None
remaining_waiting, prefills = (self.waiting, remaining_waiting, prefills = (self.waiting,
SchedulerPrefillOutputs.create_empty()) SchedulerPrefillOutputs.create_empty())