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 supported52 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Multimodal image inputs fail on /v1/responses while identical inputs work on /v1/chat/completions
- Fix gpt-oss-20b NVFP4 (ModelOpt) inference
- Fix: Calculate ITL using exact token delta from usage stats (#27485)
- [Frontend][Responses] Accept chat-completions image format on /v1/responses (#46631)
- [Bugfix] Fix UVA offload fallback copies
- [ROCm][DSV4][Kernel] Add gfx950 HIP compressor path
- [CPU] Fix shared-memory all-reduce deadlock across nodes
- [RFC]: Reduce multimodal payload in token-in/token-out by deferring `pixel_values` preprocessing to `/generate`
- [Rust Frontend] Avoid redundant decode per token in incremental detokenizer
- [Attention] Occupancy-gated 3D segmented decode for multi-query (diffusion-LM canvas) over long KV
- Docs
- Python not yet supported