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 supported7 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Developed the PoC of dAttention support. It will utilize the similar idea of vAttention, but it introduces a new memory layout that overcomes the waste of memory of vAttention.
- [Bug]: 'invalid argument' Error with custom_all_reduce when doing tensor parallelism
- [Usage]: LLama-3.1-405B Inference with vLLM TPU
- [Bug]: Lora refuses to load from disk without extremely weird manipulations with file paths
- [Usage]: Benchmarking Issues: Low Success Rate and Tensor Parallel Size Constraints on 8x AMD MI300x GPUs
- [Performance]: Transformers 4.45.1 slows down `outlines` guided decoding
- mLlama load error with non-default vocabulary sizes
- [Roadmap] vLLM Roadmap Q4 2024
- [Usage]: Default input and output sequence length for ShareGPT dataset
- [Bugfix][Hardware][Neuron] Fix getting version of neuronxcc
- Docs
- Python not yet supported