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
- [Bugfix][KV Offload] Advertise complete chunks as retrievable cache units
- [Benchmark] Add sweep warmup and failure recovery
- Recipes staged sweep workflow
- [Perf][Startup] Keep torch._inductor out of import vllm (restore #40056 lazy import)
- [Perf][Startup] Move atomic_writer out of weight_utils so the model-info cache save stays light
- [Offload] Avoid /dev/shm mmap file leak in TieringOffloadingSpec on non-graceful shutdown (#57303)
- [Perf][MRV2] Fuse final Gumbel sampler argmax and gather
- [Feature] Skip MLA weight absorption when weights are pre-processed
- [Frontend] Support CustomToolCall in the non-Harmony Responses API
- [Frontend] Replay Responses reasoning via encrypted_content blobs
- Docs
- Python not yet supported