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
- [Feature]: Support HuggingFaceM4/idefics2-8b as vision model
- [Bug]: vllm how to load Yarn-Mistral-7B-128k(24G 4090, maybe max-model-len*black-size limits max-seq-len)
- [Usage]: RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
- [Feature]: beam search mode to allow for more options in sampling process
- [Usage]: slow inference for fine-tuned model
- [Bug]: KeyError: 'dbrx'
- [Misc]: RuntimeError: Cannot find any model weights [vllm=0.4.0]
- [Usage]: why can't the `max_model_len` be greater than `max_position_embeddings` for llama2?
- Add support for ReFT
- [Misc]: Odd number GPU utilization?
- Docs
- Python not yet supported