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
- [Bugfix][Model] Fix Qwen4Exp MTP buffer placement, config parsing, and Triton warmup
- [RFC]: Return `routed_experts` on the terminal streaming chunk
- [Perf] Flatten mergeable multi-branch allOf for xgrammar structured output
- [Feature][Core] Support draining in-process requests before sleep
- [Rust Frontend] Transport terminal routed-expert payloads over gRPC
- DSpark checkpoints exported in fill-in (DFlash 1+N) layout silently serve with <1% acceptance: the optional layout flag is absent from their configs, and the default anchor-first sampler is wrong for them
- [Bugfix][Spec Decode][Structured Output] Identify draft-token hand-off snapshots (#54437)
- [Bugfix][Quantization] Keep MXFP4 weight-only checkpoints on W4A16 path (#56770)
- [watermarking] add context deduplication support to speculative decoding
- [MRV2] Cache multimodal prefix ranges per request
- Docs
- Python not yet supported