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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf][CUDA] Programmatic dependent launch for the DSA decode kernels
- [Model][Perf] Overlap mixed GDN decode and prefill recurrent kernels
- [Bug]: Kimi-K3 prefix cache miss when prompt length is exactly a 1536-token boundary
- [Feature]: Add DFly speculative decoding and D-Cut support(Related to issue 50245)
- [Bugfix][ROCm] Reject incompatible mixed KV-cache layouts
- [Bugfix] Fix TurboQuant cache dtype propagation and FP8 store on Ampere
- fix(entrypoints): migrate Responses API validation errors to VLLMValidationError
- Docs/output token control sampling params
- Fix UVA fallback for environments without pinned memory support (e.g. WSL2)
- [Bugfix] Strip Gemma4 trailing sentinels regardless of order
- Docs
- Python not yet supported