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 supported42 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Security] Fix remote DoS from grammar-rejected spec tokens padded with -1
- [Bug] ValueError: Following weights were not initialized from checkpoint (Gemma 4 models with KV sharing)
- Fix negative cudagraph memory estimate
- fix: Pin Ray placement group bundles to allowlisted nodes during scale up
- [Metrics] Add per-request preemption histogram (vllm:request_num_preemptions)
- [Frontend] Reduce multimodal preprocessing cache contention
- [Model] Optimize Qwen3-VL image preprocessing with compact patches
- [Model] Add Orthrus model support (autoregressive path)
- [Bugfix][Frontend] pythonic tool parser: accept negative numbers / unary ops as literal arguments
- [KVConnector] Add prefix-length threshold for lazy SimpleCPUOffloadConnector
- Docs
- Python not yet supported