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]: premature stopping or cut off output
- [Bug]: `pt_main_thread` processes are not killed after main process is killed in MP distributed executor backend
- [Usage]: How to inference a model with medusa speculative sampling.
- [Feature]: chat API assistant prefill
- [Usage]: Pipeline Parallelism but with quantized model?
- [Bug]: --max-model-len configuration robustness
- [Bug]: qwen2-72b-instruct model with RuntimeError: CUDA error: an illegal memory access was encountered
- [Performance]: Medusa SD have poor performance than baseline
- [Feature]: support Mistral-Large-Instruct-2407 function calling
- [Bug]: N-gram spec_decode in flash_attention bug
- Docs
- Python not yet supported