Intro

• [ ] https://hanlab.mit.edu/courses/2023-fall-65940
• [ ] https://openai.com/research/block-sparse-gpu-kernels

LM

• [ ] Weight-Decomposed Low-Rank Adaptation

  • [ ] (Unofficial) https://github.com/catid/dora

  • [ ] https://arxiv.org/abs/2402.09353

    

• [ ] https://github.com/Vahe1994/AQLM

  

References

• [ ] https://github.com/openai/blocksparse