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
- [Frontend] Add APIs for dynamic LoRA models load/unload
- [Feature]: Enable chunked prefill for neuron & cpu workers
- [Bug]: determine_num_available_blocks is not precision
- [Bug]: cannot load model back due to [does not appear to have a file named config.json]
- [Usage]: If I use Offline way to launch the model, how can I get the metrics?
- [Usage]: Is fused_moe/fused_moe.py only support num_expert= 8 and 16?
- [Usage]: How to start vllm with llava using docker compose
- [Feature]: Sliding window attention in a fraction of layers
- [Bug]: Token accuracy not as expected ad also got Junk values for starcoderbase-15b model with continuous batching
- [Performance]: Profile & optimize the BlockManagerV2
- Docs
- Python not yet supported