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 supported31 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Fix #40004: [Feature]: Priority scheduling supports preemption of requests in the
- [Misc] Add and enable Triton kernel unit tests on XPU
- [Model] Enable LoRA support for tower and connector in Voxtral
- [Bug]: `--override-generation-config` silently drops `eos_token_id` from model's `generation_config.json` — Gemma 4 tool-calling generation never stops
- [Bug]: fastapi error '_IncludedRouter' object has no attribute 'path'
- docs: clarify NIXL KV connector metrics aggregation semantics
- refactor: rename flashinfer_utils.py to flashinfer_moe.py
- EngineCore init failure reports empty "Failed core proc(s): {}" — no PID or underlying error when the core subprocess is killed during init
- docs: clarify audio chunking is non-overlapping in transcription guide
- [Bugfix] Avoid scheduler crash on stale KV transfer completion for already-freed requests
- Docs
- Python not yet supported