Skip to content

@usyd-fsalab FSA

Change the repository type filter

All

    Repositories list

    7 repositories

    • fp6_llm

      Public
      An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).
      Cuda
      •
      Apache License 2.0
      •15•211•2•0•Updated Oct 28, 2024Oct 28, 2024

    • blog

      Public
      Public repo for HF blog posts
      Jupyter Notebook
      •752•0•0•0•Updated Oct 25, 2023Oct 25, 2023

    • FSA

      Public
      Webpage for FSA
      HTML
      •0•2•0•0•Updated Oct 3, 2023Oct 3, 2023

    • flash-llm

      Public
      Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
      Cuda
      •
      Apache License 2.0
      •15•2•0•0•Updated Sep 24, 2023Sep 24, 2023

    • ReadingList

      Public
      0•12•0•0•Updated Apr 27, 2022Apr 27, 2022

    • NeuralNetworkRandomness

      Public
      Python
      •
      MIT License
      •0•14•0•0•Updated Mar 18, 2022Mar 18, 2022

    • ConferenceTalk

      Public
      Conference talks given by FSA Lab, University of Sydney
      0•1•0•0•Updated Jul 28, 2021Jul 28, 2021