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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CPU] feat: Add Vedic 4-bit matmul for MLA attention
- [Bugfix][TurboQuant] Fix dangling decode scratch when workspace grows after cudagraph capture
- [CPU][Spec Decode] Support DFlash speculative decoding for GDN models on CPU
- [Bugfix] MoRIIO toy P/D proxy: fix DP-rank index aliasing + harden for high-concurrency bursts
- [Feature] Add routed experts statistics collection with REST API
- [Attention][DSA] support dcp for FLASHINFER_MLA_SPARSE
- [Rust Frontend] Support `truncate_prompt_tokens` and `truncation_side`
- [ROCm][AITER] Directly Implement AITER Custom All-reduce in CudaCommunicator
- First Attempt at Pod Snapshotting
- [Model Runner V2] Enable cross layers KV Cache
- Docs
- Python not yet supported