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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix(lightning_attn): make CBLOCK device-aware to fit Ampere SMEM
- Support Responses API input in tokenize endpoint
- [Bug]: [kv_offload+HMA] Fails on chat subsequent request
- [Bugfix] Improve error messages for LoRA+speculative and attention_backend config conflicts
- [Misc] Reduce `time vllm --help` and `time vllm serve --help` to <1s warm
- Make VoyageEmbeddingModel.forward signature explicit
- [Feature] Add rolling-hash repetition detection algorithm
- Add comments before logs used for benchmarking.
- [RFC] Universal Translator: TP topology flexibility framework (Phase 1: ConstraintGroupedNorm + Ling pilot)
- Add metadata support to latency and throughput benchmarks
- Docs
- Python not yet supported