LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

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

Other

aiter

AI Tensor Engine for ROCm

OtherEmerging
GitHub
Stars
—
Forks
—
Contributors
8
Last push
4mo ago

Recent commits

Latest commits.

  • Add `fused_qk_norm_rope_2way` horizon fusion kernel for Qwen-Image model (#1969)
    eef90e7Yutao Xu4mo ago
  • add rmsnorm CK_TILE_FLOAT_TO_BFLOAT16_DEFAULT compile config (#1979)
    a0123a4zhyajie4mo ago
  • [CK_TILE][FMHA] Add FP8 KV_BLOCKSCALE support for batch prefill (#1975)
    e225f34Jeff Huang4mo ago
  • Fix the precision issue of allreduce (#1967)
    64faa90yanboshao4mo ago
  • syncing with latest ck (#1977)
    5accacfKhushbu Agarwal4mo ago
minor update for mla f8 v3 kernel (#1962)
0a699a7liyjiang4mo ago
  • Add allreduce rmsnorm 1stage fusion pass (#1949)
    7842709Yutao Xu4mo ago
  • hipBLASLt online tuning (#1800)
    6284a83Han Lin4mo ago

    • Top contributors

    Builders behind this project.

    valarLip
    181 commits
    gyohuangxin
    95 commits
    junhaha666
    95 commits
    slippedJim
    61 commits
    amd-ruitang3
    56 commits
    rahulbatra85
    52 commits
    ZhangLirong-amd
    47 commits
    yzhou103
    45 commits