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 supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Guided Decoding Schema Cache Store
- [Bug]: Tokenization Mismatch Between HuggingFace and vLLM
- [WIP][Kernel] A100 FP8 Quantization Method and Kernel for PhiMOE
- [Usage]: RuntimeError: Failed to infer device type (Intel Iris Xe Graphics)
- [MISC] add a flag --lazy-capture-cuda-graph to allow cuda graph capture only happens on-demand
- [Bug]: Assert Error: len(seqs) == 1
- [Performance]: Talk about the model parallelism
- [Bug]: RuntimeError: Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing, you must use the 'spawn' start method
- [Usage]: Train Lora with frozen vllm model
- [Usage]: How to use BitsAndBytesConfig with vllm serve
- Docs
- Python not yet supported