OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-07 00:21:07 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity
release/1.6
pytorch/ios
History
Ashkan Aliabadi 9184c9832e
Re-apply PyTorch pthreadpool changes (#40951) 
* Re-apply PyTorch pthreadpool changes

Summary:
This re-applies D21232894 (b9d3869df3) and D22162524, plus updates jni_deps in a few places
to avoid breaking host JNI tests.

Test Plan: `buck test @//fbandroid/mode/server //fbandroid/instrumentation_tests/com/facebook/caffe2:host-test`

Reviewed By: xcheng16

Differential Revision: D22199952

fbshipit-source-id: df13eef39c01738637ae8cf7f581d6ccc88d37d5

* Enable XNNPACK ops on iOS and macOS.

Test Plan: buck run aibench:run_bench -- -b aibench/specifications/models/pytorch/pytext/pytext_mobile_inference.json --platform ios --framework pytorch --remote --devices D221 (9788a74da8)AP-12.0.1

Reviewed By: xta0

Differential Revision: D21886736

fbshipit-source-id: ac482619dc1b41a110a3c4c79cc0339e5555edeb

* Respect user set thread count. (#40707)

Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/40707

Test Plan: Imported from OSS

Differential Revision: D22318197

Pulled By: AshkanAliabadi

fbshipit-source-id: f11b7302a6e91d11d750df100d2a3d8d96b5d1db

* Fix and reenable threaded QNNPACK linear (#40587)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/40587

Previously, this was causing divide-by-zero only in the multithreaded
empty-batch case, while calculating tiling parameters for the threads.
In my opinion, the bug here is using a value that is allowed to be zero
(batch size) for an argument that should not be zero (tile size), so I
fixed the bug by bailing out right before the call to
pthreadpool_compute_4d_tiled.

Test Plan: TestQuantizedOps.test_empty_batch

Differential Revision: D22264414

Pulled By: dreiss

fbshipit-source-id: 9446d5231ff65ef19003686f3989e62f04cf18c9

* Fix batch size zero for QNNPACK linear_dynamic (#40588)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/40588

Two bugs were preventing this from working.  One was a divide by zero
when multithreading was enabled, fixed similarly to the fix for static
quantized linear in the previous commit.  The other was computation of
min and max to determine qparams.  FBGEMM uses [0,0] for [min,max] of
empty input, do the same.

Test Plan: Added a unit test.

Differential Revision: D22264415

Pulled By: dreiss

fbshipit-source-id: 6ca9cf48107dd998ef4834e5540279a8826bc754

Co-authored-by: David Reiss <dreiss@fb.com>
2020-07-06 06:58:25 -07:00
..
TestApp Re-apply PyTorch pthreadpool changes (#40951) 2020-07-06 06:58:25 -07:00
.gitignore Add iOS test app skeleton (#26261) 2019-09-17 11:06:57 -07:00
LibTorch.h Change the source link in podspec (#26089) 2019-09-13 15:00:31 -07:00
LibTorch.podspec [iOS] 1.5.0 Cocoapods Release (#37039) 2020-04-22 10:36:18 -07:00
README.md Update the link for iOS demo app in README.md (#27145) 2019-10-03 13:43:58 -07:00

README.md

PyTorch for iOS

Cocoapods Developers

PyTorch is now available via Cocoapods, to integrate it to your project, simply add the following line to your Podfile and run pod install

pod 'LibTorch'

Import the library

For Objective-C developers, simply import the umbrella header

#import <LibTorch/LibTorch.h>

For Swift developers, you need to create an Objective-C class as a bridge to call the C++ APIs. We highly recommend you to follow the Image Classification demo where you can find out how C++, Objective-C and Swift work together.

Disable Bitcode

Since PyTorch is not yet built with bitcode support, you need to disable bitcode for your target by selecting the Build Settings, searching for Enable Bitcode and set the value to No.

LICENSE

PyTorch is BSD-style licensed, as found in the LICENSE file.