LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

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

Other

ao

PyTorch native quantization and sparsity for training and inference

OtherEmerging
GitHub
Stars
—
Forks
—
Contributors
8
Last push
21mo ago

Recent commits

Latest commits.

  • Optimize 3-bit packing
    93ff876Scott Roy21mo ago
  • float8 training axiswise scaling support with per-gemm-argument configuration (#940)
    dec0313Vasiliy Kuznetsov21mo ago
  • add axiswise scaling to Float8Linear (#920)
    e76db70Vasiliy Kuznetsov21mo ago
  • Activation Aware Weight Quantization (AWQ) (#743)
    f81fe11Pawan Jayakumar21mo ago
  • Dynamic Float8 benchmarking llama (#1017)
    92dd5f5Apurva Jain21mo ago
add axiswise granularity to Float8Tensor (#919)
52d27a1Vasiliy Kuznetsov21mo ago
  • Refactor `tiktoken` import bare except (#1024)
    e7331abMatthew Hoffman21mo ago
  • Use `importlib.util.find_spec` to check if `lm_eval` is installed instead of trying to import it (#1023)
    e2301e9Matthew Hoffman21mo ago
  • Top contributors

    Builders behind this project.

    jerryzh168
    134 commits
    HDCharles
    56 commits
    cpuhrsch
    45 commits
    gau-nernst
    38 commits
    vkuzo
    31 commits
    jcaip
    30 commits
    andrewor14
    27 commits
    metascroy
    20 commits