Skip to content
View JerryGJX's full-sized avatar
  • Massachusetts Institute of Technology
  • Cambridge, MA
  • 02:55 (UTC -04:00)

Highlights

  • Pro

Block or report JerryGJX

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
JerryGJX/README.md
  • 👋 Hi, I’m @JerryGJX

Pinned Loading

  1. mit-han-lab/Block-Sparse-Attention mit-han-lab/Block-Sparse-Attention Public

    A sparse attention kernel supporting mix sparse patterns

    C++ 540 57

  2. mit-han-lab/flash-moba mit-han-lab/flash-moba Public

    C++ 252 10

  3. mit-han-lab/fouroversix mit-han-lab/fouroversix Public

    Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”

    Python 200 24