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
- Cannot use gpt2-xl on multi-GPU
- Task was killed due to the node running low on memory
- v100 ζΎε‘
- The returned results using prompt_logprobs=1
- What do you think about integrating packing inference?
- Compiled model with torch.compile, unfortunately without performance improvements
- PowerInfer : using a combination of cpu and gpu for faster Inference
- awq compression of llama 2 70b chat got bad result
- OOM with meta-llama/Llama-2-70b-chat-hf
- Compute perplexity/logits for the prompt
- Docs
- Python not yet supported