vllm-project/vllm
Auf GitHub ansehen[Feature]: Implement Concurrent Partial Prefills In V1 Engine
Open
#14.003 geöffnet am 28. Feb. 2025
feature requesthelp wantedunstale
Repository-Metriken
- Stars
- Â (80.034 Stars)
- PR-Merge-Metriken
- Â (Durchschn. Merge 3T 17h)Â (993 gemergte PRs in 30 T)
Beschreibung
đ The feature, motivation and pitch
In V0, we support concurrent partial prefills to avoid TTFT latency with long requests. Implement it in V1
cc @WoosukKwon
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.