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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [DO NOT LAND] Prototype for Helion linear backend
- [DBO] Disallow DBO in multinode deployments when using the DeepEP High Throughput all2all backend.
- [ROCm][CI] Cache Rust builds by source inputs
- Enable asymmetric (zero_point) quant for Humming kernel
- [Bugfix][Parser] Thread token IDs through non-streaming paths of parser engine
- [CI Flaky test]: Flaky batch invariant test with FLEX_ATTENTION
- [Core] Skip building unused per-step scheduler-output fields
- [kv_offload] Emit secondary-tier BlockStored presence events
- [Frontend][KV Connector] Plumb request session id to Mooncake worker
- [M3] Enable FlashInfer A2A for Minimax-M3-MXFP8
- Docs
- Python not yet supported