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
- [RFC]: Per-request scheduling for MLA chunked context (prefill)
- [KVConnector][NIXL] Support packed MLA KV layouts in pipeline-parallel push prefill
- [XPU][INC] Add int4 w4a8 (dynamic int8 activation) backend for INC linear layers
- [CI]Resolved the Ascend NPU test build image fail.
- [Feature]: Allow an explicit expert override of the startup KV capacity check
- [MoE][Humming] Support SiTU activation for Kimi-K3
- [Bugfix][MoE] Fix padding-row handling in contiguous-layout all2all
- [XPU] update UMD to 26.27
- Feat/spec decode under pipeline parallel
- [ROCm][CI] Add missing test coverage for upstream parity
- Docs
- Python not yet supported