vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Qwen4Exp] Pin the offloaded PLE table at its exact size
- [Perf][DSv4.1] Register CPU-offloaded Engram tables at their exact size
- [Core] Add startup snapshot capture to ordinary serving
- [Kernel][Quant] Fuse MLA v_up_proj output quantization (WIP, #43498)
- [CI] Automatic quarantine for flaky tests (per hardware backend)
- [Bugfix][CPU] Replace fixed-table sampling with bucketed rejection
- [Bug]: NIXL connector calls one NIXL agent from two threads, and the agent is created without a thread sync mode
- [Bug]: NIXL pull: an aborted request whose READ never completes keeps its decode KV blocks until restart
- [Bugfix][NIXL] Time out stalled KV loads and release aborted pulls
- [Bugfix][NIXL] Serialize NIXL agent calls across connector threads
- Docs
- Python not yet supported