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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- ci: route gpu_1_queue tests to h200_35gb queue
- [CI] Fix "AMD: Entrypoints Integration (API Server openai - Part 3)" failure
- [SpecDecode] Support DFlash with FlashInfer
- [kv_offload] Fix OffloadingSpec crash on DeepSeek-V4-Flash and hybrid KV cache models
- [Core] Add shmem-aware autotune pruner for non-H100 Triton kernels
- [Model Runner V2][Spec Decode] Support spec decode with draft model
- [XPU] Fix CUDA API shims breaking Torch Dynamo during AOT compile
- [Bug][PD] Bidirectional KV transfer produces incorrect results when reasoning traces are stripped between turns
- [WIP] Enable FlashInfer checkpointing SSU for Mamba STP
- [Bugfix] Use realistic top_k in _dummy_sampler_run to avoid SM120 startup hang
- Docs
- Python not yet supported