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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: can not clean up the memory usage after instantiating the LLM class.
- [Bug]: async engine failure when placing multi lora adapter under load
- [Bug]: nsys cannot track the cuda kernel called by the process except rank 0
- [Bug]: Model Launch Hangs with 16+ Ranks in vLLM
- bug fixed: cuda out of memory lead to 'AsyncEngineDeadError: Background loop has errored already.
- [Usage]: How can I deploy llama3-70b on a server with 8 3090 GPUs with lora and CUDA graph.
- how to compile with GLIBCXX_USE_CXX11_ABI=1
- [Misc]: vllm ONLY allocate KVCache on the first device in CUDA_VISIBLE_DEVICES
- MLC
- Support for Contrastive Search
- Docs
- Python not yet supported