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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: pythonic / llama4_pythonic tool parsers return a tool call when streaming but raw text when not (trailing prose, leading-underscore names)
- [Feature]: Add decode-priority prefill cadence for single-node decode ITL
- [Bugfix][Model] Make Glm5NextMoE.forward rank-agnostic
- [RFC]: Per-position target token logprobs for prefill scoring
- [CI] Add DCP generation parity e2e and schedule Kimi DCP tests in CI
- [ROCm][Bugfix][Spec Decode][DCP] Align ranks before DFlash speculator graph capture
- Enable Kimi K3 shared expert sharding with DeepEP v2
- [DeepEPv2] Add ibstat to the container image
- [RFC]: Add NCP-OLMo support and NCP DFlash speculative decoding
- [Rust Frontend] Allow late gRPC requests during discovery withdrawal
- Docs
- Python not yet supported