LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

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

Other

FBGEMM

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

OtherEmerging
GitHub
Stars
—
Forks
—
Contributors
8
Last push
6mo ago

Recent commits

Latest commits.

  • Update sparse_ops.py to use generic gpu target fbgemm_gpu:input_combine to support both nvidia and AMD (#2905)
    a300568Frank Li23mo ago
  • Call finish_checkpoint_resume to flush optimizer step (#2884)
    15a4de5Wang Zhou23mo ago
  • Add benchmark EmbeddingSpMDMNBitBenchmarkOutTypeFloat16 (#2901)
    0e561d4Xiangyang (Mark) Guo23mo ago
  • Remove importing GlobalWeightDecayDefinition in split_table_batched_embeddings_ops (#2904)
    2808977Wang Zhou23mo ago
  • CK FP8 Gemm Optimization (#2893)
    cf6c9dcJosh Fromm23mo ago
Make `iter` persistent and add kernel check (#2897)
42d1320Supadchaya Puangpontip23mo ago
  • Replace with powf (#2896)
    3dad495Supadchaya Puangpontip23mo ago
  • Refactor vec copy in masked_index_put_kernel (#2861)
    10d2f58Sarunya Pumma23mo ago

    • Top contributors

    Builders behind this project.

    jianyuh
    348 commits
    jspark1105
    321 commits
    q10
    282 commits
    sryap
    154 commits
    dskhudia
    141 commits
    spcyppt
    65 commits
    r-barnes
    40 commits
    jasonjk-park
    35 commits