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
- [Misc]: Source code compilation vllm failed Installation Environment: A40-48G python=3.11 cuda-12.1
- [Feature]: vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving
- [DOC] Correct warning about performance
- Llama3 Inference Optimization
- [Draft] [Speculative decoding] Use SPMD worker to reduce control plane communication
- [Bug] model:DeepSeek-V2-Chat-0628 bug: ChildProcessError: worker died
- [Bug]: The num_generation_tokens in stats is incorrect with speculative decoding
- [Bug]: CUDA OOM error when loading another model after exiting the first one.
- [Performance]: Discussion about optimizing _prepare_model_input_tensors
- [Usage]: Does Prefix Caching currently support offloading to the CPU?
- Docs
- Python not yet supported