-
Notifications
You must be signed in to change notification settings - Fork 6k
Pull requests: PaddlePaddle/Paddle
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Performance] Optimize strided transpose and fp8 1x128 quantization
#79743
opened Sep 4, 2026 by
DanielSun11
Contributor
Loading…
[Performance] Optimize strided transpose and fp8 1x128 quantization
#79742
opened Sep 4, 2026 by
DanielSun11
Contributor
Loading…
[Cherry-Pick][Performance] Partition Muon 2D params per dtype to restore comm fusion
#79741
opened Sep 4, 2026 by
AlAuAu
Contributor
Loading…
[Performance] Partition Muon 2D params per dtype to restore comm fusion
#79740
opened Sep 4, 2026 by
AlAuAu
Contributor
Loading…
[Review] Add release PR review source rules
#79739
opened Sep 3, 2026 by
liuhao2638
Contributor
Loading…
[Execute Infrastructure] Rename ai_edited_test to coverage_test
#79738
opened Sep 3, 2026 by
liuhao2638
Contributor
Loading…
[Operator Mechanism] Remove unbind int32 element limit
#79737
opened Sep 3, 2026 by
omoYang
Contributor
Loading…
[Cherry-Pick][CI] Update approval check list- #79735
skip-ci: all
#79736
opened Sep 3, 2026 by
omoYang
Contributor
Loading…
[Cherry-Pick][FlexCheckpoint] Add AOA statement generation support
skip-ci: api-benchmark
skip-ci: Doc-Preview
skip-ci: slice
#79734
opened Sep 2, 2026 by
wangbingguang2026
Contributor
Loading…
[Operator Mechanism ] Add compatible logsumexp cuda kernel
#79732
opened Sep 2, 2026 by
omoYang
Contributor
Loading…
[Cherry-Pick][Operator Mechanism]Add CUDA small-stride index gradient kernel
#79731
opened Sep 2, 2026 by
feixi139
Contributor
Loading…
[Performance Optimization] optimize cummax/cummin GPU scan kernels
#79729
opened Sep 2, 2026 by
omoYang
Contributor
Loading…
[ROCm][Fix] Don't hard-fail when CUPTI is absent (ROCm >= 6)
contributor
External developers
#79726
opened Sep 1, 2026 by
palmoni5
Loading…
[VMM] Add GPU memory history recorder with Python stack capture (#79609)
#79722
opened Sep 1, 2026 by
Difers
Contributor
Loading…
[release/3.4] Sync bot approval rules from #79714
skip-ci: all
#79721
opened Aug 31, 2026 by
liuhao2638
Contributor
Loading…
[API Compatibility No.98] Add torch-compatibility for paddle.linalg.lstsq -part
contributor
External developers
#79719
opened Aug 30, 2026 by
Arctic1010
Loading…
[Operator Mechanism] Fix gradient and bounds handling of strided views
#79718
opened Aug 29, 2026 by
feixi139
Contributor
Loading…
[Operator Mechanism]Add CUDA small-stride index gradient kernel
#79716
opened Aug 28, 2026 by
feixi139
Contributor
Loading…
[Bug Fix] Align External developers
Conv1D/2D/3D default init with PyTorch (Uniform(±1/√fan_in)) to fix activation explosion in deep/weight-shared stacks
contributor
#79711
opened Aug 27, 2026 by
youge325
Contributor
Loading…
[Operator Mechanism] Align cosine_similarity with torch2.12
#79710
opened Aug 27, 2026 by
omoYang
Contributor
Loading…
fix test standard
contributor
External developers
#79708
opened Aug 27, 2026 by
greenhandF
Contributor
Loading…
align trunc_normal with torch for gpu
contributor
External developers
#79703
opened Aug 26, 2026 by
greenhandF
Contributor
Loading…
[Operator Mechanism] Add comment for sufficient big tensor IndexT guards
#79700
opened Aug 26, 2026 by
omoYang
Contributor
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-09-01.