gpo.zugaina.org

Search Portage & Overlays:

dev-python/tokenspeed-mla-bin

TokenSpeed multi-head latent attention CUDA kernels

Screenshots

  • tokenspeed-mla-bin-0.2.8
    ~amd64
    python_single_target_python3_12 python_single_target_python3_13 python_single_target_python3_14 debug

    View      Download      Browse     License: MIT   
    Overlay: stuff
  • tokenspeed-mla-bin-0.2.7
    ~amd64
    python_single_target_python3_12 python_single_target_python3_13 python_single_target_python3_14

    View      Download      Browse     License: MIT   
    Overlay: stuff
  • tokenspeed-mla-bin-0.2.6
    ~amd64
    python_single_target_python3_12 python_single_target_python3_13 python_single_target_python3_14

    View      Download      Browse     License: MIT   
    Overlay: stuff
  • tokenspeed-mla-bin-0.1.8
    ~amd64
    python_single_target_python3_12 python_single_target_python3_13 python_single_target_python3_14

    View      Download      Browse     License: MIT   
    Overlay: stuff

Reverse Dependencies

dev-python/vllm
Reverse dependancies are sometimes conditional based on your USE flags, Ebuild version and sometimes other packages. please keep this in mind.