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
- [Usage]: How to Calculate QPS Metric for vllm-Deployed Model Service Using Raw Query in Prometheus?
- [Bug]: An error occurred while using H20 to perform multi machine inference 405B through the ray cluster, causing inference to crash.
- [Bug]: error when the concurrency reaches 10 with gptq4bits
- [Feature]: Build custom_ops for both CPU and CUDA
- [Misc]: Debugging the paged attention issue for customized LLMs
- [Installation]: build error from source on P40 in container
- [Usage]: Inference metrics printing problem
- [Bug]: vllm0.6.2 Using FLASHINFER to start VLLM reported an error, enabling -- quantification gptq -- kv cache dtype fp8_e5m2
- [Installation]: build error from source on 4090
- [Usage]: VLLM 0.6.2 includes vllm-flash-attn, is it no longer necessary to install flash-attn separately?
- Docs
- Python not yet supported