24 Commits (5cccfbc61ba4e67de63eecacd564373b7ddb0e3a)

Author SHA1 Message Date
  mindspore-ci-bot ac3c35c329 !2749 GPU update argmaxwithvalue 5 years ago
  VectorSL f49b8ad6d2 update argmaxwithvalue 5 years ago
  lizhenyu 7bbe183e6f bugfix:Attr of axis of ReduceSum is invalid 5 years ago
  VectorSL 46afb18e25 update argmaxwithvalue 5 years ago
  VectorSL 17377912ba gpu add argmaxwithvalue 5 years ago
  VectorSL 8c1bd6c589 gpu refactor cuda datatype 5 years ago
  VectorSL efdfbee9df gpu slice support null output 5 years ago
  VectorSL f1bd5abaef gpu fix slice 5 years ago
  caifubi 5b963aef2b Change uintptr_t to void ptr 5 years ago
  wilfChen 83151509dc UnsortedSegmentSum kernel support Nd 5 years ago
  wilfChen 1991a89f40 LayerNormGrad fix & codex 5 years ago
  VectorSL 9996e0d4d2 gpu update shape infer 5 years ago
  wilfChen 59c4cf256c gpu support broadcast kernels 5 years ago
  mindspore-ci-bot 0edc6d254a !370 Gpu Support UnsortedSegmentSum kernel 5 years ago
  wilfChen 31f3611f9a gpu support UnsortedSegmentSum kernel 5 years ago
  ZPaC d3936b9f2a GPU kernels adapt with special dimensions. 5 years ago
  mindspore-ci-bot f602970990 !323 Gpu Concat support 4 inputs 5 years ago
  mindspore-ci-bot 4e25fec769 !324 Gpu Slice kernel performance improve 5 years ago
  VectorSL 1d7fe758a0 gpu add test for amp 5 years ago
  limingqi107 2891f0d20d gpu dynamic memory pool supports multi-allReduce 5 years ago
  wilfChen cc93646207 gpu concat kernel support 4 inputs 6 years ago
  wilfChen 5b7790a2a7 Gpu Slice kernel performance improvement 6 years ago
  VectorSL d248b05a98 gpu add kernel select 6 years ago
  zhunaipan 930a1fb0a8 initial version 6 years ago