Skip to content

GitLab

Unverified Commit 243ed7d3 authored by PiteXChen's avatar PiteXChen Committed by GitHub
Browse files

[Bugfix][Core] running queue index leakage exception (#26754) 


Signed-off-by: default avatarCLFutureX <chenyongqyl@163.com>
parent 7e094105
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
vllm/v1/core/sched/scheduler.py
View file @ 243ed7d3
...@@ -278,6 +278,7 @@ class Scheduler(SchedulerInterface): ...@@ -278,6 +278,7 @@ class Scheduler(SchedulerInterface):
token_budget += num_scheduled_tokens[preempted_req.request_id] token_budget += num_scheduled_tokens[preempted_req.request_id]
req_to_new_blocks.pop(preempted_req.request_id) req_to_new_blocks.pop(preempted_req.request_id)
num_scheduled_tokens.pop(preempted_req.request_id) num_scheduled_tokens.pop(preempted_req.request_id)
req_index -= 1
else: else:
preempted_req = self.running.pop() preempted_req = self.running.pop()
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment