[10/25] 이준형 LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

[veritas9872]

Date: 2022.10.25 Presenter: Joonhyung Lee

ArXiv: https://arxiv.org/abs/2208.07339 Blog: https://timdettmers.com/2022/08/17/llm-int8-and-emergent-features Blog: https://huggingface.co/blog/hf-bitsandbytes-integration GitHub: https://github.com/TimDettmers/bitsandbytes