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 supported47 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [MoE Refactor] Only use RouterMethodType for flashinfer
- [Hybrid] Simplify mamba block size logic for `all` mode
- [WIP] PCP simplification
- [Bugfix] Handle empty/whitespace tool_call arguments in chat preproce…
- [Feature]: LongCat-Flash-Lite and "Engram" embedding support
- [Usage]: I want to learn a hack method to offload and load vllm internal weights between CPU and GPU
- [RFC]: Native support for Mamba, SSM, and hybrid transformer models in vLLM V1
- [Feature]: Add support for Apple MPS(Metal Performance Shaders)
- [RFC]: Disaggregated Everything - Token In <> Token Out API Server
- [bug fix] disable memory pool to release unused `bf16` weights
- Docs
- Python not yet supported