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]: Command-R incorrect output contains `<EOS_TOKEN>` and seems to do text prediction rather than conversation
- [Bugfix] Adds outlines performance improvement
- [Performance]: A few performance-related questions.
- [Feature]: Adopt Colossal Inference Features (55% speedup over vLLM)
- [Usage]: extractive question answering using VLLM
- [Feature]: How to Enable VLLM to Work with PreTrainedModel Objects in my MOE-LoRA? THX
- [Usage]: how should I do data parallelism using vLLM?
- [Bug]: torch.cuda.OutOfMemoryError: CUDA out of memory when Handle inference requests
- [Feature]: MoE kernels (Mixtral-8x22B-Instruct-v0.1) are not yet supported on CPU only ?
- [Bug]: vLLM api_server.py when using with prompt_token_ids causes error.
- Docs
- Python not yet supported