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
- [Bug]: Issue when benchmarking the dynamically served LoRA adapter
- [Bug]: INTEL GPU ARC 770 import vllm error
- [Misc]: RuntimeError: CUDA error: invalid configuration argument
- [Doc] update the debugging document to add more explanation on `gpu_memory_utilization` and CUDA OOM issues
- [Feature]: Quantisation Support with CPU Backend
- [Bug]: Mistral file names are hardcoded in vllm, making fine tunes tough to use
- [Misc]: Speed of serving Starcoder models
- [Feature]: APC introspection interface
- [Performance]: Suitable draft model for llama3.1 8b
- [Bug]: benchmark_serving.py generates different numbers of tokens at different runs
- Docs
- Python not yet supported