LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

  • Markets
  • Builders
  • Research
  • Ecosystems
  • Launchpads
  • Search
Ecosystems

Other

BackendBench

How to ship your LLM generated kernels to PyTorch

OtherEmerging
GitHub
Stars
—
Forks
—
Contributors
8
Last push
9mo ago

Recent commits

Latest commits.

  • Refactor LLM backend to allow for performance based retries (#166)
    fe0915cSahan Paliskara9mo ago
  • Adding example code to train nanoGPT using BackendBench with LLM generated kernels (#165)
    b67c2d9jiannanWang9mo ago
  • Added Performance tests (#158)
    d04e86fParam Thakkar9mo ago
  • Add test for LLM backend (#159)
    35d23d6wychi9mo ago
  • Fix geneated kernel file got overwritten (#161)
    982cd36wychi9mo ago
Enable BackendBench context manager (#157)
75b76acMark Saroufim9mo ago
  • Fix an exception in using LLM backend (#156)
    61c467cwychi9mo ago
  • WIP: make compile_kernel_from_string as an util (#154)
    64bfe12Matej Sirovatka9mo ago

    • Top contributors

    Builders behind this project.

    PaliC
    27 commits
    jiannanWang
    13 commits
    msaroufim
    9 commits
    bertmaher
    7 commits
    wychi
    3 commits
    shaahins
    2 commits
    Laurawly
    1 commits
    manuelcandales
    1 commits