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 supported2 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [CI/Build] Add linting for github actions workflows
- [Bug]: vllm0.5.5+Prefix caching RuntimeError: CUDA error: an illegal memory access was encountered
- [Usage]: benchark_throughput works with hf backend but not vllm, suspect user error
- [Bug]: Cannot use model with shorter context as draft model
- [New Model]: Request to integrate Chexagent Multimodel in vLLM
- [Usage]: Bizarre Responses from vLLM and Cerebrium setup
- [Doc]: Using awq with tensor-parallel-size 4 get bad result but with tensor-parallel-size 2 get good result
- [Bug]: run failed on 8*H20
- [Usage]: set num_crops in LVLM
- [CI/Build] Added OpenVINO backend tests run
- Docs
- Python not yet supported