8186af5a26
[BE][Easy] set end-of-line for .bat file to CRLF in .editorconfig ( #156032 )
...
See also:
54976bca10/.gitattributes (L1)https://github.com/pytorch/pytorch/pull/156032
Approved by: https://github.com/seemethere , https://github.com/ezyang
2025-07-08 05:40:57 +00:00
bdacf08b86
[BE][Easy] add .editorconfig setting for C/C++/CUDA/ObjC ( #157692 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157692
Approved by: https://github.com/ezyang
2025-07-08 05:37:15 +00:00
987314aa96
Split batch-num-heads grid dim between y and z ( #157745 )
...
for #157018
doesn't totally fix the problem but should help alot
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157745
Approved by: https://github.com/Chillee
2025-07-08 05:17:43 +00:00
39a8f66d59
[BE] Use simdgroup_size constexpr ( #157751 )
...
Instead of every shader defining it separately, move it to `c10/metal/common.h`
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157751
Approved by: https://github.com/Skylion007 , https://github.com/dcci
ghstack dependencies: #157746
2025-07-08 03:46:20 +00:00
0b73f7c871
[EZ][BE] Move array def to c10/metal/common.h ( #157746 )
...
And use proper type aliasing instead of weird _ARRAY_NS
Also use `uint64_t` instead of `ulong`
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157746
Approved by: https://github.com/Skylion007 , https://github.com/dcci
2025-07-08 03:46:20 +00:00
a4c7e7f983
[PowerPC]: Fixed build issue that occur because of datatype f8 enablement for onednn in qlinear and prepack ( #157469 )
...
Getting the build issue because of enablement of data type fp8 for onednn in qlinear and qlinear_prepack file after this commit c2185dc4a5626848df37cad214b73d5ae7dd4f17
Currrently cpuinfo is disable for power system because of that it is giving below error.
**Error:**
‘cpuinfo_has_x86_amx_int8’ was not declared in this scope
Made a required changes and now build issue got fixed.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157469
Approved by: https://github.com/malfet
2025-07-08 03:45:06 +00:00
3ee8828c87
[1/N] Don't use CUDA.cmake module ( #157188 )
...
Small changes before removing CUDA.cmake.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157188
Approved by: https://github.com/ezyang
2025-07-08 03:05:35 +00:00
f56bfb3030
[CPU] Fix memory access for sbgemm bf16 ( #156585 )
...
Fixes #156022 .
1. The original dtype conversion overwrites the whole `n_*ldc_` instead of `n_*m_` with stride `ldc_`, causing the potential memory issue.
2. Fix the None value issue in attention backward UT, as the sbgemm bf16 could be used.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156585
Approved by: https://github.com/mingfeima , https://github.com/aditew01 , https://github.com/ezyang
2025-07-08 02:36:28 +00:00
12f9942b10
Fix slice op redistribute_cost compute ( #157178 )
...
For slice op backward, my understanding is that the `redistribute_cost` attribute is incorrectly assigned to previous placement strategy: 0decd966af/torch/distributed/tensor/_ops/_tensor_ops.py (L399-L400)2815ade9a8/torch/distributed/tensor/_sharding_prop.py (L491-L499)https://github.com/pytorch/pytorch/pull/157178
Approved by: https://github.com/XilunWu
2025-07-08 02:28:59 +00:00
c5589074e6
[SymmMem] find_path does not search /usr/local/lib ( #157695 )
...
This PR uses `find_library` to replace `find_path`.
It also searches for NVSHMEM host lib and device lib separately.
Tested against system install location: /usr/local/lib and /usr/local/include.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157695
Approved by: https://github.com/Skylion007
ghstack dependencies: #157513
2025-07-08 01:21:59 +00:00
30a1cc11a4
Revert "[CI][MacOS] Add VENV_PATH to search path ( #157749 )"
...
This reverts commit 85111cd165f108ffabb4a90083d59d7a867ebd9f.
Reverted https://github.com/pytorch/pytorch/pull/157749 on behalf of https://github.com/huydhn due to It looks like lint was not green, so revert and reland I guess ([comment](https://github.com/pytorch/pytorch/pull/157749#issuecomment-3047032909 ))
2025-07-08 01:18:16 +00:00
19a01382bc
Revert "[SymmMem] find_path does not search /usr/local/lib ( #157695 )"
...
This reverts commit 3effe0c293219b00a0eae7e139fe2d9aed84bc03.
Reverted https://github.com/pytorch/pytorch/pull/157695 on behalf of https://github.com/kwen2501 due to Changing it to be landable on 2.8 branch ([comment](https://github.com/pytorch/pytorch/pull/157695#issuecomment-3047020152 ))
2025-07-08 01:12:01 +00:00
df72078fe1
[dynamo] Replace unimplemented with unimplemented_v2 in torch/_dynamo/variables/torch.py ( #157344 )
...
Fixes part of #147913
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157344
Approved by: https://github.com/williamwen42
Co-authored-by: William Wen <william.wen42@gmail.com >
2025-07-08 00:46:56 +00:00
85111cd165
[CI][MacOS] Add VENV_PATH to search path ( #157749 )
...
When building/testing PyTorch on MacOS
Shoudl prevent some flakiness when conda environment overtakes CI/CD
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157749
Approved by: https://github.com/atalman , https://github.com/huydhn
2025-07-08 00:38:37 +00:00
edf7bb4f51
Fix unbound local when an error occurs before pool is initialized ( #156750 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156750
Approved by: https://github.com/jamesjwu
2025-07-08 00:28:21 +00:00
bbb930aba2
Bump urllib3 from 2.2.2 to 2.5.0 in /tools/build/bazel ( #156390 )
...
Bumps [urllib3](https://github.com/urllib3/urllib3 ) from 2.2.2 to 2.5.0.
- [Release notes](https://github.com/urllib3/urllib3/releases )
- [Changelog](https://github.com/urllib3/urllib3/blob/main/CHANGES.rst )
- [Commits](https://github.com/urllib3/urllib3/compare/2.2.2...2.5.0 )
---
updated-dependencies:
- dependency-name: urllib3
dependency-version: 2.5.0
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-07-07 17:13:21 -07:00
60b41de0ca
remove allow-untyped-defs from torch/ao/nn/quantized/modules/rnn.py ( #157234 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157234
Approved by: https://github.com/jingsh
ghstack dependencies: #157231 , #157232
2025-07-08 00:11:52 +00:00
e38a335d7f
remove allow-untyped-defs from torch/backends/cusparselt/__init__.py ( #157232 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157232
Approved by: https://github.com/jingsh
ghstack dependencies: #157231
2025-07-08 00:11:52 +00:00
9d8cf24b3b
remove allow-untyped-defs from torch/_classes.py ( #157231 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157231
Approved by: https://github.com/jingsh
2025-07-08 00:11:52 +00:00
be56a8d7ac
Automatically load and save dynamo entries via caching_precompile ( #155913 )
...
This PR adds a new config option, `caching_precompile`, and a `DynamoCache`, which loads and saves Dynamo Cache entries automatically. It also hooks up DynamoCache to PrecompileContext, so that we can save multiple cache entries.
When this configuration is turned on, we:
- Automatically create and initialize a CompilePackage on every torch.compile
- Automatically use BundledAutogradcache
- Automatically save the CompilePackage entry to DynamoCache after every compile
You can also use PrecompileContext.serialize() to manually serialize a full object.
I've added unit tests to exhibit this behavior.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/155913
Approved by: https://github.com/zhxchen17
2025-07-07 23:57:17 +00:00
3effe0c293
[SymmMem] find_path does not search /usr/local/lib ( #157695 )
...
This PR uses `find_library` to replace `find_path`.
It also searches for NVSHMEM host lib and device lib separately.
Tested against system install location: /usr/local/lib and /usr/local/include.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157695
Approved by: https://github.com/Skylion007
ghstack dependencies: #157513
2025-07-07 23:16:45 +00:00
2fde2090d0
[inductor_collectives] Make reorder_collectives_preserve_peak pass grouping nodes ( #157706 )
...
Differential Revision: [D77861765](https://our.internmc.facebook.com/intern/diff/D77861765 )
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157706
Approved by: https://github.com/wconstab
2025-07-07 23:13:58 +00:00
5d8d126249
Fix einops x torch.compile interaction ( #157600 )
...
Fixes https://github.com/pytorch/pytorch/issues/157451
If/when einops releases a version greater than 0.8.1, it will just break
(without this patch).
The history is:
- Between 2.6 and 2.7, we tried to delete the einops import (#142847 )
- That didn't work so well, so we applied a hotfix in 2.7.1. (#153925 )
- The hotfix wasn't completely correct (0.8.1 is the latest version of
einops, so the condition in the hotfix just always evaluates to True!)
- It turns out we didn't need to delete the einops import. We already
do not eagerly import einops.
- I reverted the code back to the state it was in in 2.6.
https://github.com/pytorch/pytorch/blob/release/2.6/torch/_dynamo/decorators.py
Test Plan:
- We have testing in CI for einops 0.6.1, 0.7.0, and 0.8.1. Wait for CI.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157600
Approved by: https://github.com/guilhermeleobas , https://github.com/anijain2305
ghstack dependencies: #157416
2025-07-07 23:04:02 +00:00
378c121d5e
Remove unnecessary warnings during the ATen compilation process. ( #157703 )
...
Comparing uint32_t(num_threads()) with int(kCUDABlockReduceMaxThreads) always results in a compilation warning. Just change the return type of kCUDABlockReduceMaxThreads to uint32_t to avoid it.
Fixes https://github.com/pytorch/pytorch/issues/157701
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157703
Approved by: https://github.com/malfet , https://github.com/Skylion007
2025-07-07 22:49:38 +00:00
7e83d50845
Inductor logging + analysis of torch.profile ( #149697 )
...
Prereqs:
- https://github.com/pytorch/pytorch/pull/152708
Features:
1. Adds inductor's estimate of flops and bandwidth to the json trace events that perfetto uses.
1. Only use the tflops estimation from triton if we don't have the info from the datasheet because Triton's estimates are inaccurate. I have a backlog item to fix triton flops estimation upstream. New `DeviceInfo` class, and new function `get_device_tflops`.
1. New helpers `countable_fx` and `count_flops_fx` helps get the flops of an `fx.Node`.
1. Extends Triton `torch.profiler` logging to `DebugAutotuner`.
1. New script `profile_analysis.py`: `--augment_trace` adds perf estimates to any perfetto json trace, `--analyze` creates a summary table of these perf estimates, and `--diff` will compare two traces side by side:
```python
Device(NVIDIA H100, 0):
Kernel Name | resnet Kernel Count | resnet FLOPS | resnet bw gbps | resnet Dur (ms) | resnet Achieved FLOPS % | resnet Achieved Bandwidth % | newresnet Kernel Count | newresnet FLOPS | newresnet bw gbps | newresnet Dur (ms) | newresnet Achieved FLOPS % | newresnet Achieved Bandwidth %
---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
triton_poi_fused__native_batch_norm_legi | 24 | 0 | 0.11395268248131513 | 2.5919166666666666 | 0 | 0.003401572611382541 | 24 | 0 | 0.11395268248131513 | 2.5919166666666666 | 0 | 0.003401572611382541
sm90_xmma_fprop_implicit_gemm_f32f32_tf3 | 142 | 16932673552.422373 | 0.2585007824198784 | 12.441619718309857 | 0.08683422334575583 | 0.007716441266265022 | 142 | 16932673552.422373 | 0.2585007824198784 | 12.441619718309857 | 0.08683422334575583 | 0.007716441266265022
triton_red_fused__native_batch_norm_legi | 39 | 0 | 0.13990024992108846 | 5.752589743589743 | 0 | 0.004176126863316074 | 39 | 0 | 0.13990024992108846 | 5.752589743589743 | 0 | 0.004176126863316074
triton_poi_fused__native_batch_norm_legi | 25 | 0 | 0.31824055917536503 | 2.5291999999999994 | 0 | 0.009499718184339253 | 25 | 0 | 0.31824055917536503 | 2.5291999999999994 | 0 | 0.009499718184339253
void cutlass::Kernel2<cutlass_80_tensoro | 98 | 16211056473.596165 | 0.42972434051025826 | 7.130408163265306 | 0.08313362294151874 | 0.012827592254037562 | 98 | 16211056473.596165 | 0.42972434051025826 | 7.130408163265306 | 0.08313362294151874 | 0.012827592254037562
triton_red_fused__native_batch_norm_legi | 73 | 0 | 0.3225381327611705 | 9.987068493150682 | 0 | 0.009628003963020014 | 73 | 0 | 0.3225381327611705 | 9.987068493150682 | 0 | 0.009628003963020014
triton_poi_fused__native_batch_norm_legi | 15 | 0 | 1.4491211346487216 | 4.439333333333333 | 0 | 0.043257347302946926 | 15 | 0 | 1.4491211346487216 | 4.439333333333333 | 0 | 0.043257347302946926
void cutlass::Kernel2<cutlass_80_tensoro | 186 | 14501701145.337954 | 0.2667131401910989 | 7.873865591397849 | 0.07436769818122027 | 0.007961586274361157 | 186 | 14501701145.337954 | 0.2667131401910989 | 7.873865591397849 | 0.07436769818122027 | 0.007961586274361157
triton_poi_fused__native_batch_norm_legi | 33 | 0 | 1.4924556538193923 | 4.3101515151515155 | 0 | 0.044550915039384846 | 33 | 0 | 1.4924556538193923 | 4.3101515151515155 | 0 | 0.044550915039384846
triton_red_fused__native_batch_norm_legi | 29 | 0 | 0.25562590522631107 | 6.296275862068965 | 0 | 0.007630624036606301 | 29 | 0 | 0.25562590522631107 | 6.296275862068965 | 0 | 0.007630624036606301
triton_poi_fused__native_batch_norm_legi | 13 | 0 | 0.5870562174192726 | 2.7397692307692307 | 0 | 0.01752406619162008 | 13 | 0 | 0.5870562174192726 | 2.7397692307692307 | 0 | 0.01752406619162008
triton_poi_fused__native_batch_norm_legi | 34 | 0 | 0.41409928846284 | 2.853588235294117 | 0 | 0.012361172789935523 | 34 | 0 | 0.41409928846284 | 2.853588235294117 | 0 | 0.012361172789935523
triton_per_fused__native_batch_norm_legi | 34 | 0 | 0.11705315007018151 | 3.460647058823529 | 0 | 0.0034941238826919864 | 34 | 0 | 0.11705315007018151 | 3.460647058823529 | 0 | 0.0034941238826919864
triton_poi_fused__native_batch_norm_legi | 16 | 0 | 0.17207853197124584 | 2.3459375000000002 | 0 | 0.005136672596156592 | 16 | 0 | 0.17207853197124584 | 2.3459375000000002 | 0 | 0.005136672596156592
triton_per_fused__native_batch_norm_legi | 30 | 0 | 0.2639714322022256 | 6.131199999999999 | 0 | 0.007879744244842555 | 30 | 0 | 0.2639714322022256 | 6.131199999999999 | 0 | 0.007879744244842555
sm90_xmma_fprop_implicit_gemm_f32f32_tf3 | 100 | 11875430356.891787 | 0.19494470869421385 | 16.36534 | 0.06089964285585531 | 0.005819245035648175 | 100 | 11875430356.891787 | 0.19494470869421385 | 16.36534 | 0.06089964285585531 | 0.005819245035648175
triton_poi_fused__native_batch_norm_legi | 8 | 0 | 0.9854096626224687 | 3.2757500000000004 | 0 | 0.029415213809625928 | 8 | 0 | 0.9854096626224687 | 3.2757500000000004 | 0 | 0.029415213809625928
void cublasLt::splitKreduce_kernel<32, 1 | 56 | 34377923395.147064 | 0.8310300045762317 | 3.4199999999999986 | 0.17629704305203628 | 0.024806865808245714 | 56 | 34377923395.147064 | 0.8310300045762317 | 3.4199999999999986 | 0.17629704305203628 | 0.024806865808245714
triton_poi_fused__native_batch_norm_legi | 23 | 0 | 0.9944002965861103 | 3.2431304347826084 | 0 | 0.02968359094286896 | 23 | 0 | 0.9944002965861103 | 3.2431304347826084 | 0 | 0.02968359094286896
triton_per_fused__native_batch_norm_legi | 10 | 0 | 0.1826801058931057 | 4.428800000000001 | 0 | 0.00545313748934644 | 10 | 0 | 0.1826801058931057 | 4.428800000000001 | 0 | 0.00545313748934644
triton_poi_fused__native_batch_norm_legi | 10 | 0 | 0.3168973585366449 | 2.5471999999999997 | 0 | 0.009459622642884923 | 10 | 0 | 0.3168973585366449 | 2.5471999999999997 | 0 | 0.009459622642884923
triton_poi_fused__native_batch_norm_legi | 34 | 0 | 1.1463614897015777 | 4.124323529411764 | 0 | 0.03421974596124114 | 34 | 0 | 1.1463614897015777 | 4.124323529411764 | 0 | 0.03421974596124114
void cask_plugin_cudnn::xmma_cudnn::init | 44 | 44045510816.64277 | 2.0661232850348643 | 3.6887499999999993 | 0.22587441444432194 | 0.06167532194133924 | 44 | 44045510816.64277 | 2.0661232850348643 | 3.6887499999999993 | 0.22587441444432194 | 0.06167532194133924
sm90_xmma_fprop_implicit_gemm_f32f32_tf3 | 95 | 7876855400.165316 | 0.4694941555946739 | 18.224315789473682 | 0.04039413025725802 | 0.014014750913273854 | 95 | 7876855400.165316 | 0.4694941555946739 | 18.224315789473682 | 0.04039413025725802 | 0.014014750913273854
triton_per_fused__native_batch_norm_legi | 41 | 0 | 0.06825669875995298 | 3.0384146341463416 | 0 | 0.002037513395819492 | 41 | 0 | 0.06825669875995298 | 3.0384146341463416 | 0 | 0.002037513395819492
triton_poi_fused__native_batch_norm_legi | 23 | 0 | 0.08808154712430301 | 2.3275652173913044 | 0 | 0.0026292999141582997 | 23 | 0 | 0.08808154712430301 | 2.3275652173913044 | 0 | 0.0026292999141582997
triton_per_fused__native_batch_norm_legi | 40 | 0 | 0.18179321034952417 | 4.556825 | 0 | 0.005426662995508183 | 40 | 0 | 0.18179321034952417 | 4.556825 | 0 | 0.005426662995508183
triton_poi_fused__native_batch_norm_legi | 15 | 0 | 0.5887415155454232 | 2.783866666666667 | 0 | 0.017574373598370836 | 15 | 0 | 0.5887415155454232 | 2.783866666666667 | 0 | 0.017574373598370836
void cutlass::Kernel2<cutlass_80_tensoro | 38 | 14242013806.264643 | 0.256592404353939 | 7.217631578947369 | 0.0730359682372546 | 0.007659474756834 | 38 | 14242013806.264643 | 0.256592404353939 | 7.217631578947369 | 0.0730359682372546 | 0.007659474756834
triton_poi_fused__native_batch_norm_legi | 21 | 0 | 0.5842860973430516 | 2.7779047619047623 | 0 | 0.017441376040091088 | 21 | 0 | 0.5842860973430516 | 2.7779047619047623 | 0 | 0.017441376040091088
triton_per_fused__native_batch_norm_legi | 16 | 0 | 0.11509365173486417 | 3.5959375000000002 | 0 | 0.0034356313950705724 | 16 | 0 | 0.11509365173486417 | 3.5959375000000002 | 0 | 0.0034356313950705724
triton_poi_fused__native_batch_norm_legi | 14 | 0 | 0.1704672000243914 | 2.4044285714285714 | 0 | 0.00508857313505646 | 14 | 0 | 0.1704672000243914 | 2.4044285714285714 | 0 | 0.00508857313505646
triton_poi_fused__native_batch_norm_legi | 58 | 0 | 2.307520779930795 | 8.190706896551722 | 0 | 0.06888121731136704 | 58 | 0 | 2.307520779930795 | 8.190706896551722 | 0 | 0.06888121731136704
triton_per_fused__native_batch_norm_legi | 29 | 0 | 0.037243248971881276 | 3.0277586206896556 | 0 | 0.001111738775280038 | 29 | 0 | 0.037243248971881276 | 3.0277586206896556 | 0 | 0.001111738775280038
triton_poi_fused__native_batch_norm_legi | 20 | 0 | 0.04741699795428918 | 2.2911500000000005 | 0 | 0.0014154327747549007 | 20 | 0 | 0.04741699795428918 | 2.2911500000000005 | 0 | 0.0014154327747549007
triton_per_fused__native_batch_norm_legi | 25 | 0 | 0.13357016893727824 | 3.37536 | 0 | 0.003987169222008305 | 25 | 0 | 0.13357016893727824 | 3.37536 | 0 | 0.003987169222008305
triton_poi_fused__native_batch_norm_legi | 13 | 0 | 0.3089862268300253 | 2.8111538461538457 | 0 | 0.009223469457612694 | 13 | 0 | 0.3089862268300253 | 2.8111538461538457 | 0 | 0.009223469457612694
triton_poi_fused__native_batch_norm_legi | 17 | 0 | 0.3129385387909844 | 2.673 | 0 | 0.009341448919133863 | 17 | 0 | 0.3129385387909844 | 2.673 | 0 | 0.009341448919133863
triton_per_fused__native_batch_norm_legi | 19 | 0 | 0.2215568162533158 | 3.8837368421052636 | 0 | 0.0066136363060691275 | 19 | 0 | 0.2215568162533158 | 3.8837368421052636 | 0 | 0.0066136363060691275
std::enable_if<!(false), void>::type int | 23 | 504916805.19297093 | 1.0118296096314707 | 8.113913043478261 | 0.0025893169497075447 | 0.030203868944223014 | 23 | 504916805.19297093 | 1.0118296096314707 | 8.113913043478261 | 0.0025893169497075447 | 0.030203868944223014
triton_poi_fused_add_copy__38 | 56 | 0 | 0 | 2.132482142857143 | 0 | 0 | 56 | 0 | 0 | 2.132482142857143 | 0 | 0
triton_poi_fused_convolution_0 | 18 | 0 | 0.43458610794936897 | 2.773333333333334 | 0 | 0.012972719640279667 | 18 | 0 | 0.43458610794936897 | 2.773333333333334 | 0 | 0.012972719640279667
triton_poi_fused_convolution_1 | 17 | 0 | 0.028816312469162712 | 2.6145882352941174 | 0 | 0.0008601884319153051 | 17 | 0 | 0.028816312469162712 | 2.6145882352941174 | 0 | 0.0008601884319153051
void convolve_common_engine_float_NHWC<f | 44 | 8641868995.31118 | 0.024730540008465626 | 25.87327272727273 | 0.04431727689903169 | 0.0007382250748795709 | 44 | 8641868995.31118 | 0.024730540008465626 | 25.87327272727273 | 0.04431727689903169 | 0.0007382250748795709
triton_per_fused__native_batch_norm_legi | 12 | 0 | 0.6809930918986744 | 4.82675 | 0 | 0.020328151996975356 | 12 | 0 | 0.6809930918986744 | 4.82675 | 0 | 0.020328151996975356
triton_per_fused__native_batch_norm_legi | 14 | 0 | 0.02883030597936608 | 2.6651428571428575 | 0 | 0.0008606061486377935 | 14 | 0 | 0.02883030597936608 | 2.6651428571428575 | 0 | 0.0008606061486377935
triton_per_fused__native_batch_norm_legi | 16 | 0 | 0.0014658988233201874 | 2.098 | 0 | 4.375817383045335e-05 | 16 | 0 | 0.0014658988233201874 | 2.098 | 0 | 4.375817383045335e-05
triton_poi_fused__native_batch_norm_legi | 13 | 0 | 0.9926297180284697 | 3.2367692307692306 | 0 | 0.02963073785159611 | 13 | 0 | 0.9926297180284697 | 3.2367692307692306 | 0 | 0.02963073785159611
triton_poi_fused__native_batch_norm_legi | 9 | 0 | 1.3008817095666507 | 3.0863333333333336 | 0 | 0.03883228983781048 | 9 | 0 | 1.3008817095666507 | 3.0863333333333336 | 0 | 0.03883228983781048
void at::native::(anonymous namespace):: | 98 | 0 | 0.09174335613709389 | 4.408520408163265 | 0 | 0.0027386076458833994 | 98 | 0 | 0.09174335613709389 | 4.408520408163265 | 0 | 0.0027386076458833994
void at::native::vectorized_elementwise_ | 7 | 0 | 0 | 1.7278571428571428 | 0 | 0 | 7 | 0 | 0 | 1.7278571428571428 | 0 | 0
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/149697
Approved by: https://github.com/eellison , https://github.com/shunting314
2025-07-07 22:13:34 +00:00
6f05d58f2b
[AOTI] Split aoti_runtime/model.h to prepare for model static linking ( #157592 )
...
Summary:
Prepare for https://github.com/pytorch/pytorch/pull/157129 .
We split the file so we can re-use `model.h` part for codegen a separate header for each model in static linkage.
Test Plan:
CI
Rollback Plan:
Differential Revision: D77761249
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157592
Approved by: https://github.com/desertfire
2025-07-07 22:13:22 +00:00
a7eb153bba
[MemoryViz] Add file selector button ( #157647 )
...
In some linux desktop environments like mine, there is no drag and dropping of files. Which made the memoryviz impossible for me to use. So this adds a file selector button as an alternative. Tested that it works locally, and also works with multiple files.
And the button remains when something is loaded, to allow loading something else, but it moves out of the way to save vertical space:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157647
Approved by: https://github.com/sraikund16
2025-07-07 22:03:51 +00:00
ed6df0e324
correctly import torch.version ( #157584 )
...
The structure is
```
torch/
__init__.py
version.py
```
When we import torch, only `torch/__init__.py` is executed by default.
The submodules like `version.py` are not automatically imported or attached to the torch module.
So without anything in `__init__.py`, `torch.version` may not be found. So in this PR, we make the import explicit.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157584
Approved by: https://github.com/ezyang
2025-07-07 21:43:35 +00:00
5c79a55e7e
[oss] Add version to metadata ( #155343 )
...
Summary: We want to add versioning to DCP to the metadata so that whenever planner logic changes, we can use the version on save to determine how to load the data
Test Plan:
added a test
Rollback Plan:
Differential Revision: D76135887
Pull Request resolved: https://github.com/pytorch/pytorch/pull/155343
Approved by: https://github.com/teja-rao
2025-07-07 20:57:30 +00:00
3d06ff82a8
[release] Triton pin update to 3.4 ( #156664 )
...
Triton pin update issue: https://github.com/pytorch/pytorch/issues/154206
Please see post: https://dev-discuss.pytorch.org/t/2-8-final-rc-release-postponed-by-a-week/3101
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156664
Approved by: https://github.com/davidberard98
2025-07-07 20:52:25 +00:00
2efa5eaa65
swa avoid stream sync ( #157705 )
...
Summary:
When AveragedModel updates_parameters it calls self.n_averaged == 0 for each parameter, where n_averated is a buffer on GPU. Moving check before the cycle to call sync once
It improves update_parameter from 74ms to 57ms ~22% improvement
{F1980011097}
{F1980011111}
Test Plan:
CI
Rollback Plan:
Differential Revision: D77723025
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157705
Approved by: https://github.com/albanD , https://github.com/Skylion007 , https://github.com/janeyx99
2025-07-07 20:47:35 +00:00
c2510fcd86
Fix index_put propagate strategy arg unpack error ( #157671 )
...
Fix `index_put` propagate strategy didn't consider optional arg `accumulate`.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157671
Approved by: https://github.com/fmassa , https://github.com/wconstab
2025-07-07 20:18:18 +00:00
510c398a4f
Add max_pool3d backward pass for MPS ( #157498 )
...
Note on backward precision over fp16:
A float16 number has 10 bits of mantissa, 5 bits of exponent, and 1 bit for the sign. If the sign bit is positive, then with a mantissa $m$ and exponent $e$ represented in base 10, the number that the float16 format represents is $(1 + m / 1024) \exp2(e)$. ([source](https://en.wikipedia.org/wiki/Half-precision_floating-point_format ))
Consider adding two numbers $a$ and $b$ which have arbitrary mantissas, and say their exponents are $e_a = 1$ (so $2 \le a \lt 4$) and $e_b=-3$ (so $0.175 \le b \lt 0.25$). Assume that the result has the same exponent as $a$. Since the exponents differ by 4, we'll effectively need to truncate the 4 rightmost bits of $b$'s mantissa, which would introduce a maximum error on the order of $(2^4 / 1024) \exp2(-3) \approx 0.002$.
The error is nearly the same if $e_b = -2$ (so $0.25 \le b \lt 0.5$), where the 3 rightmost bits are truncated, giving a maximum error on the order of $(2^3 / 1024) \exp2(-2) \approx 0.002$. Same for $e_b=-1$.
So if we're adding up nine different numbers that all have exponents -3, -2, or -1, and they sum to a number with exponent 1, then we would expect a maximum error of several times greater than 0.002. In my comments above, summing those particular nine numbers in different ways gave results that ranged between 3.1816 and 3.1758, a difference of $0.0058 \approx 2.9 * 0.002$.
That's within the acceptable bounds, and we can safely just increase the error tolerance used in test_output_grad_match for the case of max_pool3d_backward with float16.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157498
Approved by: https://github.com/malfet
2025-07-07 19:46:44 +00:00
63a96eaeb8
[DeviceMesh] Add error when users try to slice non contiguous flattened dim submesh ( #157523 )
...
With https://github.com/pytorch/pytorch/issues/157393 , we want to first throw a clearer error for users and then fix it in the long-term
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157523
Approved by: https://github.com/fegin
ghstack dependencies: #157501
2025-07-07 19:43:51 +00:00
2b8d3b1b2b
[DeviceMesh] Use user set backend and pg option even for the global mesh ( #157501 )
...
Short term solution to https://github.com/pytorch/pytorch/issues/156593 .
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157501
Approved by: https://github.com/fegin , https://github.com/lw
2025-07-07 19:43:51 +00:00
bf1ebe0531
Fix typo: 'paramter' → 'parameter' in dynamo variable comment ( #157651 )
...
This PR fixes a minor typo in a comment in `torch/_dynamo/variables/torch.py`, changing 'paramter' to the correct spelling 'parameter'.
These small but meaningful changes help improve code readability and maintain the overall quality of the codebase.
Thanks for your time and review!
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157651
Approved by: https://github.com/Skylion007
2025-07-07 19:42:44 +00:00
433a247102
[logging] [redo] dynamo_timed for CachingAutotuner.coordinate_descent_tuning ( #156840 )
...
Summary: This is a redo of https://github.com/pytorch/pytorch/pull/156517 , but with pt2_compile_events logging disabled.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156840
Approved by: https://github.com/jamesjwu
2025-07-07 19:09:48 +00:00
8a47f9d03b
[CI] Fix xpu ci test sccache issue ( #157693 )
...
With PR #157341 land, it broken the PXU CI test on sccache which has been disabled by #143851 . Re-disable it
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157693
Approved by: https://github.com/atalman , https://github.com/huydhn
2025-07-07 18:29:38 +00:00
9e5f4a844c
[FSDP2] Fix issue with set_reduce_scatter_divide_factor errors and MixedPrecisionPolicy ( #155964 )
...
fix https://github.com/pytorch/pytorch/issues/155223
Pull Request resolved: https://github.com/pytorch/pytorch/pull/155964
Approved by: https://github.com/weifengpy
2025-07-07 17:09:29 +00:00
7c1f627828
Fix 'dllimport attribute ignored on inline function' ( #157670 )
...
There are lots of warnings in builds:
```
2025-07-05T16:59:46.9208806Z C:\actions-runner\_work\pytorch\pytorch\build\aten\src\ATen\core\TensorBody.h(5043,29): warning: 'at::Tensor::less_' redeclared inline; 'dllimport' attribute ignored [-Wignored-attributes]
2025-07-05T16:59:46.9209030Z 5043 | inline at::Tensor & Tensor::less_(const at::Scalar & other) const {
2025-07-05T16:59:46.9209104Z | ^
2025-07-05T16:59:46.9209671Z C:\actions-runner\_work\pytorch\pytorch\build\aten\src\ATen\core\TensorBody.h(5048,29): warning: 'at::Tensor::less_' redeclared inline; 'dllimport' attribute ignored [-Wignored-attributes]
2025-07-05T16:59:46.9209860Z 5048 | inline at::Tensor & Tensor::less_(const at::Tensor & other) const
```
This PR has fixed them and turned the warning into an error.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157670
Approved by: https://github.com/albanD
2025-07-07 16:57:48 +00:00
b3b4d28f4c
[submodule][cutlass] Update pin to b995f93 v4.0.0 ( #157376 )
...
@Skylion007 seems afk. https://github.com/pytorch/pytorch/pull/153541
https://github.com/NVIDIA/cutlass/releases/tag/v4.0.0
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157376
Approved by: https://github.com/drisspg , https://github.com/Skylion007
2025-07-07 16:55:47 +00:00
ae1094b72b
Revert "[WIP] Automatically load and save dynamo entries via caching_precompile ( #155913 )"
...
This reverts commit e466dab164d9236bfe5817ec8e4d24c7b9d3e392.
Reverted https://github.com/pytorch/pytorch/pull/155913 on behalf of https://github.com/huydhn due to Sorry for reverting your change but it seems to fail a test in trunk ([comment](https://github.com/pytorch/pytorch/pull/155913#issuecomment-3045914878 ))
2025-07-07 16:53:35 +00:00
eda0a9cc90
[list] Add list.__delitem__ ( #156339 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156339
Approved by: https://github.com/zou3519
ghstack dependencies: #153969 , #156148 , #156242 , #156270 , #156271
2025-07-07 14:51:32 +00:00
d74ccf4ffe
[list] Add list.__mul__ and list.__imul__ ( #156271 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156271
Approved by: https://github.com/zou3519
ghstack dependencies: #153969 , #156148 , #156242 , #156270
2025-07-07 14:51:32 +00:00
689fba032d
Implement list.__add__ and list.__iadd__ ( #156270 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156270
Approved by: https://github.com/Skylion007 , https://github.com/zou3519
ghstack dependencies: #153969 , #156148 , #156242
2025-07-07 14:51:25 +00:00
c1d69d5dd5
[list] Implement list.remove ( #156242 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156242
Approved by: https://github.com/Skylion007 , https://github.com/zou3519
ghstack dependencies: #153969 , #156148
2025-07-07 14:51:17 +00:00
e49acfc5c5
[list] Raise exception in invalid list method call ( #156148 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156148
Approved by: https://github.com/zou3519
ghstack dependencies: #153969
2025-07-07 14:51:10 +00:00
034e996d37
[list] Implement list.count ( #153969 )
...
Pull Request resolved: https://github.com/pytorch/pytorch/pull/153969
Approved by: https://github.com/zou3519 , https://github.com/XuehaiPan
2025-07-07 14:51:03 +00:00
16c3b4143b
[gtest][listing] Enable gtest json listing for the fbcode/caffe2 project ( #156816 )
...
***SUMMARY***
The main function in this tests overrides that of the Gtest framework which contains it's `RUN_ALL_TESTS()` function. The main function in this test is called conditionally when conditions apply, in this case, when the C10_MOBILE directive is provided. This is wrong as we always want to call the `RUN_ALL_TEST()` function.
In this PR, we only make the test suite available for cases that apply, i.e if the C10_MOBILE directive exist which represents the caching allocator and is only exposed on mobile
***TEST PLAN***
This tests should run in modes where it applies which should be covered in the CI run.
Below shows a sample run in the dev-nosan mode which do not have the cache allocator
BEFORE
```
buck test fbcode//caffe2:cpu_caching_allocator_test
Discovered 0. Pass 0. Fail 0. Fatal 0. Skip 0. Timeout 0
⚠ Listing failed: caffe2:cpu_caching_allocator_test
Listing tests failed with error:
Failed to read from /data/users/ysuleiman/fbsource/buck-out/v2/test/buck-out/v2/test_discovery/fbcode/6dcc55a61c1b90b3/default/tpx_execution_dir/gtest_output_file.json. Listing process stdout: , stderr:
```
AFTER
```
buck test '@fbcode//mode/dev-nosan' fbcode//caffe2:cpu_caching_allocator_test
Analyzing targets. Remaining 0/46242 1871690 actions, 2251668 artifacts declared
Executing actions. Remaining 0/257870 83:28:24.4s exec time total
Command: test. Finished 10 remote, 112314 cache (99% hit) 83:22:43.5s exec time cached (99%)
Time elapsed: 2:57.7s
Tests finished: Pass 0. Fail 0. Fatal 0. Skip 0. Build failure 0
NO TESTS RAN
```
Rollback Plan:
steps:
- manual.note:
content: Revert this diff
Reviewed By: patskovn
Differential Revision: D77229077
Pull Request resolved: https://github.com/pytorch/pytorch/pull/156816
Approved by: https://github.com/kimishpatel
2025-07-07 14:16:43 +00:00
54a4d34d10
[fbcode] switch to cutlass-4 ( #157579 )
...
Summary: Update cutlass version to 4. For most use cases.
Test Plan:
testing in progress
Rollback Plan:
Differential Revision: D77605011
Pull Request resolved: https://github.com/pytorch/pytorch/pull/157579
Approved by: https://github.com/drisspg , https://github.com/Skylion007
2025-07-07 14:12:33 +00:00
