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
- [Usage]: how to view generated tokens in vllm serve
- [Bug]: min_tokens is sometimes not respected
- [RFC]: AWS Neuron 2.22 NxD Inference with vLLM V0
- [Bug]: v0.8.2, enable calculate_kv_scales, caught exception
- [Bug]: In vllm v0.7.3, passing parameter "stream_options" results in an error.
- [Bug]: can not use uv run or uv run python on mac series
- [Bug]: EADDRINUSE (-98) error when setting up NCCL communicator
- [Bug]: amd gpu Multiple graphics cards cannot function properly
- [Bug]: System gets stuck during pressure test
- [Bug]: creating helm chart with vllm image and downloaded model throws raise KeyboardInterrupt("terminated") KeyboardInterrupt: terminated error
- Docs
- Python not yet supported