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
- [Rust Frontend] Add LongCat tool parser
- [DRAFT] OPT: MergeAttention shared memory for LSE loading
- [Bug]: vllm 0.23.0 2*h20-141G mp+dep and mp +tep deploy dsv4p error
- [Bug]: DSV4-Flash MooncakeStoreConnector save never triggers when MTP speculative decoding is enabled
- [ROCm][MLA] Fuse RoPE + MLA KV-cache write via AITER Triton kernel
- [Frontend] Support count_reasoning_tokens in the Streaming Parser Engine
- fix: report stop_sequence stop_reason in Anthropic Messages API
- [Bugfix] Don't fail model load for multimodal models with no language model (#45806)
- [RFC]: Optimizing vLLM for High Beam-Width Generative Recommendation Inference
- [Bugfix] Reject pipeline parallelism for DiffusionGemma
- Docs
- Python not yet supported