CITATION.cff

cff-version: 1.2.0
message: "If you use mlx-flash in research, please cite:"
title: "mlx-flash: Flash Weight Streaming for LLM Inference on Apple Silicon"
authors:
  - family-names: Wong
    given-names: Matt K.
repository-code: https://github.com/matt-k-wong/mlx-flash
license: MIT
date-released: 2024-05-20
references:
  - type: article
    title: "LLM in a Flash: Efficient Large Language Model Inference with Limited Memory"
    authors:
      - family-names: Alizadeh
        given-names: Keivan
      - family-names: Kang
        given-names: Iman
      - family-names: Cherkasau
        given-names: Seyed Mehrshad
      - family-names: Simpson
        given-names: Josh
      - family-names: Gunst
        given-names: Jeffrey
      - family-names: Genovese
        given-names: Mark
      - family-names: Sapuntzakis
        given-names: Constantine
      - family-names: Szegedy
        given-names: Christian
      - family-names: Shali
        given-names: Ashish
    doi: 10.48550/arXiv.2312.11514