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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- feat: add BROWSER_BACKEND env var support to HarmonyBrowserTool, default to youcom
- [Perf] Build prompt mask with presence-only scatter in apply_penalties
- [Perf][Model] Build Phi4MM Conformer streaming mask on target device
- [Bugfix][KVOffload] Restore evicted CPU blocks and fix cursor advancement
- [XPU][Attention] Widen prefill BLOCK_M to 32 for power-of-2 GQA (~2x prefill on BMG)
- [XPU][Attention] Enable tensor-descriptor Q load for non-power-of-2 GQA (~1.9x Qwen2-7B)
- Fix Qwen3.5 text causal LM hybrid support
- [Rust Frontend] add functiongemma tool parser support
- [Bug]: vLLM 0.24.0 with DeepSeek on Blackwell SM120 (RTX PRO 6000) — Comprehensive Issues Report
- [Bugfix][Core] Reserve the KV null block when validating max_model_len
- Docs
- Python not yet supported