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
- [XPU] Add tuned Mamba SSU configs for Intel Arc Pro B70
- [Frontend] Add stream reasoning and tool calls from the derender endpoint
- [Bugfix] Hold a reference to fire-and-forget asyncio tasks
- [Multimodal] Add RTSP live-stream captioning via DeepStream backend
- [Bug][ROCm][MI355X] Kimi-K3 TP8 crashes in ROCM_AITER_MLA with HIP Code 700
- [XPU][UT] Fix explicit-overrides UT failure by enabling config-driven XPUGraph mode when VLLM_XPU_ENABLE_XPU_GRAPH is unset
- [Spec Decode][Core] Run an all-sliding DFlash drafter with prefix caching enabled
- [Bugfix][MRV2] Require all requests to be decoding for uniform-decode dispatch
- [Bugfix][Kimi K3] Fix chat rendering parity and response_format wiring
- [Rust Frontend] Deduplicate request preprocessing for `/tokenize`
- Docs
- Python not yet supported