← 최신 프로덕트

Recurser lib reduces GPT2-XL VRAM usage by 25% and runs it on Colab

Reduce VRAM usage on transformer models.

오픈소스

9 스타 · GitHub외부 사이트

github.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. I made a GPU VRAM calculator for transformer-based models

    vram.asmirnov.xyz

    Hacker News135점

  2. OSS implementation of Test Time Diffusion that runs on a 24gb GPU

    github.com

    The implementation of Test Time Diffusion paper by Google with some tweaks to run on 24gb gpu

    Hacker News21점

  3. Goralim

    github.com

    a rate limiting pkg for Go to handle distributed workloads

    Hacker News69점

  4. Taliesin

    medium.com

    bit-exact KV-cache restore, 21x faster, cross-GPU verified

    Hacker News10점

  5. Finetune Llama-3 2x faster in a Colab notebook

    colab.research.google.com

    Hacker News45점