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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- inital commit
- [bugfix] Solve the accuracy issue of deepseek ocr2
- [Bug]: Prefix caching ignores visual input, causing incorrect multimodal outputs under concurrency
- Vllm multi cascade attention and jct
- [Bug]: Engine core proc EngineCore_DP0 died unexpectedly, shutting down client.
- [ROCm][BugFix] Fix accuracy issue for `AiterMLABackend` for newest aiter main branch
- [gpt-oss] Add model_identity to system message retrieval for harmony chat template
- fix(gguf): Auto-select compatible dtype for GGUF models on Blackwell
- [RFC]: Token Padding Strategy for FP8 GEMM Performance Optimization
- Optimize workspace memory in DeepGEMM.
- Docs
- Python not yet supported