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 supported7 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: RuntimeError: Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you must use the 'spawn' start method
- [Usage]: How does VLLM allocate memory
- [Bug]: exceptiongroup.ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
- [Feature]: Support for compiled model graph for TPUs
- [Bug]: Assertion Error when inferencing with sample_n>1and occur preemption
- Llama3.2 Vision Model: Guides and Issues
- [Bug]: vllm api server return escaped unicode string in guided backend 'outlines'
- [Misc]: Strange `leaked shared_memory` warnings reported by multiprocessing when using vLLM
- vLLM's V1 Engine Architecture
- [Doc]: Is Qwen2.5's long context YARN handled?
- Docs
- Python not yet supported