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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix: validate ngram_gpu compatibility with disabled compilation
- [Bugfix][Core] Emit full reuse events for converged hybrid connector hits
- [Bugfix][KV Offload] Deduplicate replicated GQA heads in canonical storage
- [Feature][KV Offload] Enable canonical offload for chunked-local attention
- [Bugfix] Reject prompt_logprobs=0 with --kv-sharing-fast-prefill
- [Roadmap] Q4 2026 OPD Teacher Serving in vLLM
- [Core] Bound prefix-cache reuse for target-token prefill scoring
- [Test][Spec Decode] Regression test for #61443 (GLM-5.3-Flash DFlash shape) on draft-layer tags
- [Bugfix][Rust Frontend] Open a new assistant turn after a final assistant message in the DeepSeek V4/V4.1 renderer
- [Bugfix][Frontend] Sync DeepSeek V4.1 encoder with the 1017 reference (tool-result turns, content-block tool results)
- Docs
- Python not yet supported