Commits

Branch selector

 develop

User selector

All users

All time

Commit History

Commits on Jun 14, 2025

• 【Operator Mechanism】add fused_stack_transpose_quant api (#73228)

  Show description for 36f76e1
  ggggxm

  authored
  36f76e1

  Copy full SHA for 36f76e1

• [SOT] Mark fleet func unified && fix circular import (#73278)

  DrRyanHuang

  authored
  16ed678

  Copy full SHA for 16ed678

• Modified Event in collective_helper (#73292)

  Show description for 5e78aa7
  YqGe585

  authored
  5e78aa7

  Copy full SHA for 5e78aa7

Commits on Jun 13, 2025

• added default = 1 and axis number check (#73123)

  Show description for 17a45fb
  Qin-sx

  authored
  17a45fb

  Copy full SHA for 17a45fb

• [Auto Parallel] Add spmd rule No.9 for group_norm and group_norm_grad ops. (#72946)

  Show description for dcdd774
  Glencsa

  authored
  dcdd774

  Copy full SHA for dcdd774

• [Auto Parallel] Add spmd rule No.12 for label_smooth and label_smooth ops. (#72845)

  Show description for 0c0320f
  ooooo-create

  authored
  0c0320f

  Copy full SHA for 0c0320f

• fix _get_default_backend (#73301)

  YqGe585

  authored
  db3a842

  Copy full SHA for db3a842

• [SOT] Add dynamic shape check && rm useless info (#73287)

  DrRyanHuang

  authored
  f5ddd6f

  Copy full SHA for f5ddd6f

• [Accuracy diff No.133] Fix accuracy diff for pow API (#73274)

  Show description for c999558
  cszdrg

  authored
  c999558

  Copy full SHA for c999558

• [PHI] fix topk big tensor bug (#73110)

  Show description for bbbf608
  liuruyan

  authored
  bbbf608

  Copy full SHA for bbbf608

• [PHI] Fix masked_fill & masked_fill_grad kernel for big tensor (#73284)

  lshpku

  authored
  e7b0165

  Copy full SHA for e7b0165

• [PHI] Fix contiguous kernel for big tensor (#73275)

  lshpku

  authored
  a2c72f7

  Copy full SHA for a2c72f7

• [0-size Tensor No.133、318、277、136、320、239、325] Add 0-size Tensor support for matmul (#73094)

  co63oc

  authored
  de1c73f

  Copy full SHA for de1c73f

• [PHI] Fix paddle.trapezoid for big tensor (#73201)

  Show description for bcad368
  LCStayingdullCircuit

  authored
  bcad368

  Copy full SHA for bcad368

• [XPU] fix div 0 error in bkcl/nccl dynamic check (#73290)

  dynamicheart

  authored
  ec9ab90

  Copy full SHA for ec9ab90

• Fix (#73191)

  co63oc

  authored
  1202c7b

  Copy full SHA for 1202c7b

• opendir_check-1 (#73210)

  ApricityXX

  authored
  530bf7a

  Copy full SHA for 530bf7a

• [PHI] fix broadcast kernel for big tensor (#73105)

  Show description for d225dfe
  liuruyan

  authored
  d225dfe

  Copy full SHA for d225dfe

• [Auto Parallel] Add fused_gemm_epilogur spmd rule (#73126)

  GITD245

  authored
  7efdf31

  Copy full SHA for 7efdf31

• [Auto Parallel] Add spmd rule No.7 for expand_as and expand_as_grad ops. (#73107)

  Show description for a1ea048
  ooooo-create

  authored
  a1ea048

  Copy full SHA for a1ea048

• [Auto Parallel] add more tests for expand spmd (#73154)

  Show description for 700f6e8
  ooooo-create

  authored
  700f6e8

  Copy full SHA for 700f6e8

• [PHI] Unify expand_as, expand_as_grad kernel behavior between cpu and gpu (#73101)

  Show description for 23748bf
  ooooo-create

  authored
  23748bf

  Copy full SHA for 23748bf

• [PHI]fix softmax big tensor accuracy (#73288)

  Hongqing-work

  authored
  0df1811

  Copy full SHA for 0df1811

Commits on Jun 12, 2025

• [AutoParallel] PipelineStage (#72155)

  Show description for f728f15
  

  xuxinyi389

  and

  zty-king

  authored
  f728f15

  Copy full SHA for f728f15

• cherry pick deepep update (#73055)

  Show description for 0de3f8e
  Hongqing-work

  authored
  0de3f8e

  Copy full SHA for 0de3f8e

• [0-size Tensor Retest No.5] fix output shape diff for paddle.nanmedian (#73267)

  DanielSun11

  authored
  a6fcb93

  Copy full SHA for a6fcb93

• [0-size Tensor Retest No.4] fix shape diff for matrix_rank when input is 0-size tensor (#73263)

  Show description for 3a63fd5
  DanielSun11

  authored
  3a63fd5

  Copy full SHA for 3a63fd5

• [0-size Tensor support] fix std in some 0-size case (#73214)

  Show description for b7b57f0
  DanielSun11

  authored
  b7b57f0

  Copy full SHA for b7b57f0

• [0-size Tensor No.157、167、176、177、179、201、215、222、223、230、266] Add 0-size Tensor support for some activation function API. (#73028)

  Show description for 34b14c1
  DanielSun11

  authored
  34b14c1

  Copy full SHA for 34b14c1

• [CINN] Clean up the redundant content of poly folder (#73212)

  Show description for b02f144
  eggman-1024

  authored
  b02f144

  Copy full SHA for b02f144

• [Dy2St] Add a hook to replace run impl for partial program layer (#73081)

  SigureMo

  authored
  a519ae3

  Copy full SHA for a519ae3

• debug bernoulli inplace func (#73271)

  Show description for 6fcebc2
  Qin-sx

  authored
  6fcebc2

  Copy full SHA for 6fcebc2

• 修改tensor.data的返回，返回的张量不包含梯度信息 (#73246)

  Show description for 137c06c
  Qin-sx

  authored
  137c06c

  Copy full SHA for 137c06c

• Update NPU CI (#73025)

  Show description for e71db3c
  YqGe585

  authored
  e71db3c

  Copy full SHA for e71db3c

• 【set_value】temp fix Set tensor cuda error (#73251)

  Show description for e07e5a4
  xiaoguoguo626807

  authored
  e07e5a4

  Copy full SHA for e07e5a4

Pagination

Previous

Next