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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CI] Add opt-in statistically-calibrated lm-eval accuracy gate (Wilson lower bound)
- fix(kv_cache): domain-tag LoRA and cache_salt prefix-cache keys to prevent collision (#44701)
- [ROCm CI] 90% parity on AMD's test group gating status/mirroring by AMD Advancing AI July 22 2026
- [ROCm Test-First CI]: Day 0 vLLM MI455X UALoE72 Helios Rack open source community upstream CI by AMD Advancing AI July 22 2026
- [Rust Frontend] Add Granite tool and reasoning parsers
- fix(scaled_mm): use reshape to accept non-contiguous activations
- [Bugfix] Strip <|"|> sentinels from dict-key positions in Gemma4ToolParser
- [Bugfix] Multinode config validation
- [Bugfix][Frontend] Fix completion `max_tokens: null` returning HTTP 500
- [Bailing] Add MTP (Multi-Token Prediction) draft model support
- Docs
- Python not yet supported