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
- [Perf][MoE] Fold routed_scaling_factor into output transform weights
- [Bug]: Illegal memory access (Xid 13) with SimpleCPUOffloadConnector on Qwen3.8-Flash-Next while an async CPU→GPU prefix load is in flight / sm120
- [DOCS][Cleanup] Remove stale TODO for scaled KV cache in cp_gather_cache
- [Test] Re-enable jina-embeddings-v3 Matryoshka test on Transformers v5
- [NIXL] Bump NIXL version to 1.5.0
- [CI] Run watermarking tests on GPU nightly
- [NIXL] Validate 1.x release candidates
- [Bugfix][Spec Decode] Size the YaRN rotary cache to cover max_position
- [Bugfix][KV Connector] Retire in-flight output state on load-failure recompute
- [Bug]: `vllm bench sweep serve --resume` skips the warmup on the restarted server, and crashes after a run recorded by `--continue-on-error`
- Docs
- Python not yet supported