-
Notifications
You must be signed in to change notification settings - Fork 3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add MacOS platform support to onnxruntime-c pod #18334
Closed
Closed
Changes from 39 commits
Commits
Show all changes
161 commits
Select commit
Hold shift + click to select a range
c4460c5
add macos to build xcframework and other minor changes
e008e56
add more changes for configuring optional macos build in pod framework
3544456
enable in ios packaging pipeline and check artifacts
9dfbfae
fix input argument
46e44c6
fix
cf27c8d
adjust build settings json file for ios/macos framework
2c01018
adjust ios packaging pipeline
ad013e2
add back ios archs
af3209f
update c.podsepc.template
013b520
update framework_info.json.template
74a8b35
fix
85e9a69
remove two framework_info.json changes
2c69e12
minor updates
700a40d
add changes for build.py script to add optional --macosx behavior
3cfaaf7
minor update
b65bfab
Merge branch 'main' of https://github.com/microsoft/onnxruntime into …
4dc6369
Add FlattenAndUnpad Op (#17845)
guyang3532 7a3da45
add bfloat16 support for CUDA Neg kernel (#18306)
prathikr 55c19d6
[QNN EP] Enable option to set QNN context priority (#18315)
HectorSVC 55efb83
add softmax op support-coreml
b0a0588
Merge branch 'main' of https://github.com/microsoft/onnxruntime into …
01e746b
update
8d50313
[Migraphx EP] Static int8 QDQ support (#17931)
TedThemistokleous 2c22b49
Fix rust compile issues and add GH action to run build validations an…
devigned 25fbc2b
fix fused relu activation (#18303)
guschmue bafb0b6
comment unused params
f237b0b
[QNN EP/Quantization] Add MinimumRealRange extra option to quantizati…
adrianlizarraga 829d802
[js/webgpu] Support uniform for softmax (#18345)
axinging 1ff8948
Bump actions/stale from 4.1.1 to 8.0.0 (#18149)
dependabot[bot] 59262df
Add cuda context headers to zip (#18330)
RandySheriffH d955885
Update stale.yml to fix start-date bug (#18376)
sophies927 3e32fc5
add split op support
74705ca
updates
8f2fc30
minor change
dd1bb76
[js/webgpu] Fix scalar uniform (#18318)
axinging 87744e5
fix reference to Microsoft.GSL::GSL in CMake build scripts when enabl…
bverhagen 2d23b4e
Update min macos version (#18251)
snnn a6f8ec6
refine and fix the split op builder logic
28c23ae
[js/webgpu] Fix conv2d with activation (#18388)
qjia7 64c91d7
Fix ability to use patch on Windows CI machines (#18356)
skottmckay 8dba6ef
[js/webgpu] Add uniforms support to concat op (#18238)
axinging aee52cb
minor update
eb3518b
minor update
6b0c97b
[js/web] fix typescript type check (#18343)
fs-eire 0c8c001
[js/webgpu] Use builtin num_workgroups to fix shader key conflict (#1…
axinging d87d480
Remove deprecated vscode settings (#18349)
justinchuby 646f77a
Align context virtuals (#18396)
RandySheriffH a46c79d
fix llama2-70b bug, add document (#18398)
frank-dong-ms 8d298f6
Fix xnnpack compile error on arm32 (#18291)
skottmckay cd4b487
add support for softmax 13- cases
af462fe
unit test
f375d83
update
5dba904
update
cbf0cf0
[WebNN EP] Disable clamp fusion for WebNN GPU (#18386)
Honry 73ed34a
[WebNN EP] Support numThreads option for WebNN CPU device (#18054)
Honry 4a82030
[ORTModule] Symbolic Shape Support for Triton Codegen (#18317)
centwang 949ac4b
[js/webgpu] Support uniforms for gather (#18312)
axinging 0d22d64
Update SDXL demo and documents (#18395)
tianleiwu 4f2bd38
[QNN EP] Ensure QDQ Split input/output quant params are equal (#18332)
adrianlizarraga c3b5479
Remove extra CUDA version flag (#18397)
snnn a62a500
[ROCm] Update CK version (#17628)
PeixuanZuo f19c673
If Branch Constant Folding (#18105)
yuslepukhin 888ef95
updates
37d8bed
[ROCm] add migraphx into onnxruntime-training-rocm package (#18339)
PeixuanZuo 8ff41ae
Fix 4 more bad delegates missing the attribute that cause iOS AOT err…
skottmckay 897c1c1
Set DML package name correctly in CI (#18405)
skottmckay 0b16185
build wasm with linux (#18106)
mszhanyi a09099f
Remove XNNPack from web pipelines (#18419)
snnn 3e1cf71
[TensorRT EP] Fix bug for handling outer scope values in GetCapabilit…
chilo-ms 5aeed62
Bump axios from 1.3.4 to 1.6.1 in /js/node (#18400)
dependabot[bot] c9d5345
[QNN EP] Clean-up todo for OnnxInputInfo (#18416)
adrianlizarraga a6b515f
[QNN EP] Update Where Op UT to include the issue relate to data layou…
HectorSVC cbde30c
update build.py args
d22b1af
[js/web] add CI steps to log info for test failure investigating (#18…
fs-eire 27d0685
Remove Node.js tool installer task from web ci pipeline (#18434)
snnn 2e55138
update objc pod script
fc7926a
update framework_info path for ios/macos to make it consistent
d30ffb4
add arm64 arch in config
47ff783
modify c.podspec template
f9af940
onboard MoE (#18279)
wangyems 05526b3
Adding new yaml file for downloading cuda, and trt from azure blob (#…
jchen351 d738ff1
SDXL demo: consistent opt shape and seed (#18445)
tianleiwu b0699d9
Support Graph Input and Initializer for GatherToSplit Fusion (#18412)
centwang ed89ca5
[ORTModule] Support User Config for Triton Codegen, Bugfix for Reduce…
centwang 586f06f
[js/web] set noUnusedParameters to true and fix a few bugs (#18404)
fs-eire 0a4d76d
MLAS AArch64 quantized int4 Gemm kernel (#18031)
edgchen1 83dcadd
updates config
b653bd6
update
3e79055
fix split op logic and enable tests
cc840c5
Fix a bug in SaveInputOutputNamesToNodeMapping function (#18456)
snnn 6f863ae
Allow optional axes tensor to be null and ignore it as optional (#18423)
yuslepukhin 6f9f653
[wasm] increase test max memory from 2G to 4G (#18459)
fs-eire 18a3675
[TensorRT EP] Only instantiate TRT builder once (#18100)
chilo-ms 751aa8d
fix axis of layernorm for UpstreamReshape (#18425)
guyang3532 16d7f55
lora conv1d replacement (#16643)
zhijxu-MS e31fe55
fix softmax handling
119e86e
SDXL demo: Add Option to disable refiner (#18455)
tianleiwu 999752a
[WebNN EP] Support GreaterOrEqual and LessOrEqual ops (#18411)
Honry b291b20
[JS/Web]Added uniforms support to Slice op. (#18422)
satyajandhyala 3588fba
[TensorRT EP] Fix memory leak for cudnn/cublas (#18467)
chilo-ms b6b9aff
Allow empty shapes and do not validate them for inputs/outputs (#18442)
yuslepukhin e7a524f
Update to allow large models to be checked for mobile support. (#18357)
skottmckay 6a4e448
[QNN EP] Support Qnn MatMul with 2 dynamic inputs which are uint16 qu…
HectorSVC adb56df
Aciddelgado/gqa local (#18375)
aciddelgado 2273c98
merge nested framework_info.json
f1cb9e1
update naming
1448f36
update json templates
d8dd54b
simplier impl with softmaxnd
f17b6af
[TensorRT EP] Fix bug for no nodes in subgraph at GetCapability (#18449)
chilo-ms 1f1119f
minor updates
d73073d
remove full protobuf requirement for tensorrt ep (#18413)
jywu-msft 5eb5056
Always run emsdk_env.sh before build.py, even when ccache is disabled…
snnn 1a29460
rope support 4D input tensor (#18454)
kailums a5537f2
[WebNN Ep] Slice's axes and steps inputs should be constant initializ…
Honry fac3e33
[js/web] JSEP Attention & MultiHeadAttention (#17742)
dakenf 3a68692
build only mac arch for testing on packaging pipeline temp
06418c6
test config
41f9379
Update NDK version to 26.1.10909125 (#18493)
snnn e4acd53
expand time out
0bd59d6
address pr comments
2e89ac4
fix
0d96ebe
update
cbb85b4
[CoreML] Adapt to `MLMultiArray.dataPointer` deprecation (#17726)
NickLucche 0233329
Removed all the deprecated python training code and related tests and…
askhade 34c5424
[js] update a few packages (#18499)
fs-eire 53ea59d
add macos test package target in the test app
9364c05
Update web-ci.yml: remove depth=1 (#18500)
snnn 20cf553
update license comments
84be6eb
podfile.template
172ab19
enable macos package test in script
53917a3
Move up members in Lite Custom Op hierarchy for possible memleaks. (#…
RandySheriffH 97cc40d
Add fusion patterns for conformer-transducer model (#18461)
apsonawane dc9ab4f
Update setup.py: replace libcudart.so.12.0 with libcudart.so.12 (#18501)
snnn 3bcc137
Tiny change to trigger the update of DORT's CI image (#18507)
wschin d97fc18
Create a new Python Package pipeline for CUDA 12 (#18348)
jchen351 1af0681
Bfloat16 support for MatMulBnb4, Training support bitsandbytes>=0.41.…
jambayk 1dd9bf5
Remove setup_env_azure.bat (#18482)
jchen351 247ce21
[js] optimize eslint config (#18460)
fs-eire 65356e6
configure optional exclude macos target for not pod onnxruntime-c
cc54202
Create edges with arg positons correctly accounting for non-existing …
yuslepukhin abdf8b7
[js/webgpu] Optimize broadcast binary. (#18185)
qjia7 9630aa7
run pod deintegrater
33f5010
rename the test project
0e5c660
rename folder to apple_package_test
e306561
modify path names/xcworkspace name in pipelines, etc.
5634893
address pr comments
c7fd930
[js/web] unify resolve rules for "Clip" (#18527)
fs-eire d8d5b29
address pr comments
a608c00
fix past-kv in general LLM exporter (#18529)
wejoncy 29a409a
Add missing flags DISABLE_FLOAT8_TYPES in GemmFloat8 custom operator …
xadupre 2a01622
Hide NPU Adapter selection behind macro (#18515)
smk2007 bfa68b2
minor updates and fix ci
680a526
Training packaging pipeline for cuda12 (#18524)
ajindal1 81a763a
Make TensorShapeVector to use InlinedVector<Int64_t> to reduce on tem…
yuslepukhin ac8598a
[js/webgpu] enable f16 for concat (#18528)
qjia7 7497316
update file names
8a3e2dc
address pr comments
a86fbbd
Merge branch 'yguo/coreml-softmax-op-support' of https://github.com/m…
YUNQIUGUO 0a69346
linting
YUNQIUGUO bc30357
Merge branch 'yguo/macos-pod-support' of https://github.com/microsoft…
YUNQIUGUO b7ab82e
linting
YUNQIUGUO File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
File renamed without changes.
22 changes: 21 additions & 1 deletion
22
...orm/ios/ios_package_test/Podfile.template → ...apple/apple_package_test/Podfile.template
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
File renamed without changes.
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
currently only
onnxruntime-mobile-c
cannot run on MacOS right?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think currently I only enabled macos arch in the default_full_build_settings.json file, so training/mobile variant both don't run macos yet.