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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Tokenizer] Reject reserved special tokens in DeepSeek V4.1 requests
- [Feature]: Qwen4Exp PLE cpu_offload without UVA (NVIDIA Confidential Computing)
- [Perf][DSv4.1] Replay one row for prefill chunks far from the prompt end
- [Feature][Multimodal] Make the media fetch User-Agent configurable
- [Installation]: cu129
- [Model] Qwen4Exp: stage CPU-offloaded PLE rows on the host when UVA is unavailable
- [Bug]: DeepSeek-OCR / Unlimited-OCR fail to start on v0.32.0 — Triton CompilationError "Cannot access global variable LOG2E" in DeepEncoder rel-pos attention kernel
- [Test] Add a test for the DeepEncoder rel-pos attention kernel
- [Test][KV Offload] Cover sliding-window canonical TP round trips
- [Performance]: MultiConnector([NixlConnector, OffloadingConnector]) disables divergent local hybrid cache hits on Decode
- Docs
- Python not yet supported