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
- [New Model]: Support Zyphra/Zamba2-7B
- [Bug]: When using the latest 0.6.3, No module named 'vllm._version' appears
- [Bug]: KeyError: 'layers.60.mlp.gate_up_proj.weight' mistral large bitsandbytes
- [Usage]: Obtaining success / error rate % metrics
- [Installation]: When can release the WHL package for version v0.6.3 of cu118?
- [Installation]: v0.6.3 install -cutlass failed (Fetchcontent.cmake build step)
- [Misc]: Im trying to host my finetuned Llama -3-8b instruct in Vllm
- [Bug]: 400 Bad Request
- [Bug]: In function calls, when outputting Chinese, a backslash character "\" appears before Chinese characters.
- [Bug]: --cpu-offload-gb flag not honored in vllm/vllm-openai container on amazon g5.2xlarge
- Docs
- Python not yet supported