Skip to content

Pull requests: ROCm/pytorch

New pull request New
38 Open 1,544 Closed
38 Open 1,544 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Copy trans fixl2 miss
#1807 opened Dec 25, 2024 by coderfeli Loading…
1
[ROCm][PerfOptimizataion] Enable layernorm using ck_tile APIs
#1806 opened Dec 23, 2024 by lcskrishna • Draft
2
[ROCm][WIP] Improve performance of casted elementwise add operations
#1805 opened Dec 20, 2024 by doru1004 Loading…
2
ROCm: Support tf32
#1803 opened Dec 19, 2024 by jagadish-amd Loading…
2
[release/2.4] Enable bf16 with fp32 weights for MIOpen batchnorm
#1801 opened Dec 18, 2024 by jithunnair-amd Loading…
2
Wrap vec size 8 with USE_ROCM
#1795 opened Dec 16, 2024 by oraluben Loading…
2
[AUTOGENERATED] [release/2.5] Cherry-pick PR-1767
#1794 opened Dec 13, 2024 by rocm-mici • Draft
6
[WIP][release/2.5] refactor condition to use miopen for batchnorm
#1787 opened Dec 13, 2024 by dnikolaev-amd • Draft
7
Improve performance of reduce sum for 3D shapes
#1786 opened Dec 12, 2024 by doru1004 Loading…
5
Improve performance of reduce sum for 3D shapes
#1785 opened Dec 12, 2024 by doru1004 Loading…
2
[rocm6.3_internal_testing] remove xfail from 'batch_norm_with_update'
#1776 opened Dec 6, 2024 by dnikolaev-amd Loading…
2
[release/2.5] [user triton] Ignore backend-specific args in the TTIR analysis (#141…
#1768 opened Dec 4, 2024 by jataylo Loading…
7
[release/2.5] AMDSMI/layernorm cherry picks
#1764 opened Dec 4, 2024 by jataylo Loading…
7
[release/2.5] Fixed string comparison in test_cpp_wrapper_hipify
#1760 opened Nov 29, 2024 by iupaikov-amd Loading…
8
[release/2.5] Enabled force_shape_pad for test_pad_mm and test_slice_mm_bandwidth_computation
#1755 opened Nov 28, 2024 by iupaikov-amd Loading…
9
[Release/2.4] Use deterministic backends of scaled dot product attention for batched testing
#1749 opened Nov 26, 2024 by amd-sriram Loading…
@amd-sriram
13
[ROCm] Improve softmax performance.
#1740 opened Nov 21, 2024 by doru1004 Loading…
25
[release/2.5] Skipped some inductor tests for no hipcc rocm environments
#1697 opened Nov 13, 2024 by iupaikov-amd • Draft
16
MIOpen bf16 batchnorm enablement
#1665 opened Oct 31, 2024 by jithunnair-amd • Draft
12
[release/2.5] ModuleTracker: Add explicit garbage collection
#1661 opened Oct 30, 2024 by pragupta Loading…
19
[release/2.5][ROCm] Fix largeIndexBlockSize
#1659 opened Oct 30, 2024 by pragupta Loading…
19
[experimental][FP16] Add native __half support for sum_functor
#1655 opened Oct 29, 2024 by mhalk Loading…
38
Update build_triton_wheel.py to update base repo name for triton
#1637 opened Oct 17, 2024 by ethanwee1 Loading…
8
change tolerance for test_cublas_addmm
#1632 opened Oct 11, 2024 by ramcherukuri Loading…
44
[DONT MERGE] Test PR to test creation of comment by Pytorch CI
#1630 opened Oct 11, 2024 by inemankov Loading…
70
ProTip! no:milestone will show everything without a milestone.