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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Security]: remote media URLs allow SSRF to internal/link-local addresses by default
- [Bugfix][ROCm] Skip AITER top-k/top-p sampler on gfx942
- Added subchannel dequantization support for allspark kernel
- [Core][KV Offload] Service the P2P control plane while the engine waits on the model
- [Bugfix][MoE] Reject non-contiguous routing tensors
- [MM][Mistral] Add compile support for Pixtral vision encoders
- [KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots
- [Bugfix][MLA] Size the profile-run chunked-prefill workspace from the active backend's builder
- [Bugfix][Model] Enable pipeline parallelism for GLM-5.3-Flash (materialize deferred mHC state; load MTP drafter embedding)
- [Rust Frontend][Feature] Support separate tokenizer and config sources
- Docs
- Python not yet supported