vllm-project/vllm
[Feature]: Priority scheduling supports preemption of requests in the running queue by requests in the waiting queue
Aperta
#40.004 aperta il 16 apr 2026
feature requesthelp wanted
Metriche repository
- Star
- (80.034 stelle)
- Metriche merge PR
- (Merge medio 3g 17h) (993 PR mergiate in 30 g)
Descrizione
🚀 The feature, motivation and pitch
The current priority scheduling only supports evicting low-priority requests from the running queue when resources are insufficient. However, when scheduling the waiting queue, if pending requests cannot be scheduled (for example, when the number of requests in the running queue has reached max_num_seqs), even high-priority requests cannot preempt requests in the running queue.
Alternatives
No response
Additional context
No response
Before submitting a new issue...
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.