saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-18 21:21:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
5652 commits 2856 branches 57 tags 1.3 GiB
Commit graph

5652 commits

This branch
This branch
All branches
Author SHA1 Message Date
TomWildenhain-Microsoft
da56f01ac2
Fix bug in ReduceSum with noop_with_empty_axes (#9301) 2021-10-08 13:33:24 -07:00
Dmitri Smirnov
7b61bca6df
Fix inclusive sum overlfow when applied on int8_t buffer in Compress (#9295) 
Use thrust::transform_iterator when feeding input to cub::DeviceScan::InclusiveScan() to make sure the accumulator type is wide enough not to overflow.
 2021-10-08 11:29:28 -07:00
satyajandhyala
29379db432
Added SigmoidGrad schema and kernels. (#9244) 
* Added SigmoidGrad schema and kernels.

* Added test_sigmoid_grad function.
 2021-10-08 11:03:28 -07:00
Vincent Wang
cd65a8089e
Optimize Variadic Elementwise Ops (#9186) 
* optimize variadic elementwise ops

* remove nvvp file

* correct comment

* resolve comments
 2021-10-08 13:45:54 +08:00
Hariharan Seshadri
5f5f28bf14
Fix bug in allocation planner while planning location for initializers (#9306) 2021-10-07 19:05:07 -07:00
Tang, Cheng
68601fc296
error handling ffor eager mode's data transfer (#9261) 2021-10-07 17:16:33 -07:00
Suffian Khan
70cf61fa84
disable bart-l for now (#9305) 2021-10-07 16:55:54 -07:00
Maajid khan
72c4cea9e6
[OpenVINO-EP] V3.2 Release (#9232) 
* model caching changes for 2021.4

Signed-off-by: Your Name <you@example.com>

* changed the ov version check

* Minor changes added

Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>

* Added support for external data format

Starting from OpenVINO 2021.4 version, OpenVINO-EP
will support onnx models with Weights saved in external
file location.

Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>

* Introduced Hetero/Multi options for perf_test

Enabled to use HETERO/MULTI device feature from
OpenVINO-EP using the onnxruntime_perf_test tool.

Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>

* cleaned up CMake code for older OV version support

OV 2020.3 is now longer supported by OpenVINO-EP.
This check is not required now.

Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>

* Add option to disable graph partitioning

Added a option to diable graph partitioning
during build time for OpenVINO-EP.

with this option, when the model is not fully
supported on OpenVINO-EP, the model fully fall
backs to default CPU EP (MLAS).

Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>

* Changed the flag for diabling graph partitioning

Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>

* Fixes the flake8 check error

Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>

* Added changes for disable graph partition option

Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>

* Fixed flake8 indentation error

Signed-off-by: MaajidKhan <n.maajidkhan@gmail.com>

Co-authored-by: Your Name <you@example.com>
 2021-10-07 16:02:19 -07:00
ytaous
7166586d7e
Enable SkipCheck by default (#9215) 
* Enable SkipCheck by default

* fix UTs

* fix UT

* fix UTs

* fix UTs

* address comments

* fix UT

* enable skipchecks

* move _SkipCheck back

* move _SkipCheck back

* move _SkipCheck back

* Update orttraining/orttraining/python/training/ortmodule/_inference_manager.py

* Update orttraining/orttraining/python/training/ortmodule/_utils.py

Co-authored-by: Ethan Tao <ettao@OrtTrainingDev4.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
Co-authored-by: Thiago Crepaldi <thiago.crepaldi@microsoft.com>
 2021-10-07 15:47:14 -07:00
Yulong Wang
88d5023885
[js/web] always use new data dir for ort web E2E karma tests (#9303) 
* [js/web] always use new data dir for ort web E2E karma tests

* fix
 2021-10-07 15:27:12 -07:00
Tang, Cheng
c002dc86a3
set mpi group init flag after add group (#9293) 2021-10-07 10:09:16 -07:00
Changming Sun
4f4875b0e8 Add "workspace: clean: all" to anybuild build yaml file 2021-10-06 22:49:37 -07:00
Gary Miguel
e2b1852eec
Build: respect onnxruntime_PREFER_SYSTEM_LIB for more things (#9181) 
This is based on a patch applied locally by
https://github.com/conda-forge/onnxruntime-feedstock. Having this in
master seems useful.
 2021-10-06 13:49:28 -07:00
Thiago Crepaldi
52d067402a
Fix all-or-nothing fallback for bad ORTModule init (#9277) 
* Fix all-or-nothing fallback for bad ORTModule init

* Address comments
 2021-10-06 15:12:27 -04:00
Suffian Khan
510b58c877
Increase AMD CI pipeline timeout to 120 min (#9280) 
* increase timeout

* add timeout

* add timeout

* rename
 2021-10-06 10:43:09 -07:00
Changming Sun
334980e016 Delete nocontribops pipelines 2021-10-06 10:30:32 -07:00
baijumeswani
bcdb411c8d
Implement FusedAdam for ORT adapted from DeepSpeed (#9266) 2021-10-05 20:50:34 -07:00
Guoyu Wang
a4d53c4ab5
fix training distributed ci failure (#9273) 2021-10-05 15:36:44 -07:00
ashbhandare
35c2102cfa
Fixes for GatherND, Multinomial (#9143) 
* register gathernd kernel, aten multinomial

* fix CI, add test

* review comments
 2021-10-05 14:51:58 -07:00
G. Ramalingam
0b77c9ca7c
Cleanup function definitions of contrib ops (#9265) 
* Simplify function definitions

* Simplify fast-gelu function definition

* Simplify training function op body definitions

Signed-off-by: Ganesan Ramalingam <grama@microsoft.com>

* Eliminate redundant function

Signed-off-by: Ganesan Ramalingam <grama@microsoft.com>

* Formatting changes

Signed-off-by: Ganesan Ramalingam <grama@microsoft.com>

* Minor formatting changes

Signed-off-by: Ganesan Ramalingam <grama@microsoft.com>

* Add comment

Signed-off-by: Ganesan Ramalingam <grama@microsoft.com>

* Specify int64 type for constant 1

Signed-off-by: Ganesan Ramalingam <grama@microsoft.com>
 2021-10-05 11:38:42 -07:00
Thiago Crepaldi
6e2f66ee9c
Allow custom exporter args + bug fix (#9242) 2021-10-04 11:32:42 -04:00
Jingqiao Fu
67ff339df7
fixed a profiler.py bug (#9231) 2021-10-03 20:28:20 -07:00
ashari4
113edbda64
Add bf16 specialization for IsDataType (#9254) 
* Add bf16 specialization

* Fixed indent
 2021-10-02 07:15:06 -07:00
Sheil Kumar
8f6fd014e4
Force Windows AI NuGet pipeline to use Windows SDK 19041 (#9255) 
* Force Windows AI Nuget pipeline to use 19041 Windows SDK as 22000 casues a downlevel regression by importing LoadLibraryW

* move into quotes

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
 2021-10-01 21:46:14 -07:00
Faith Xu
9fe09cb72a
Update dockerfile readme (#9241) 
* Update dockerfiles page

* Delete Dockerfile.server

* Delete Dockerfile.training
 2021-10-01 17:28:26 -07:00
Tiago Koji Castro Shibata
11a391a88f
Port ARM64x support (#9230) 2021-10-01 13:06:43 -07:00
Guoyu Wang
60bbdf1403
Remove unused NodeArgs in Graph::Resolve (#9213) 
* Remove unused NodeArgs

* Handle case where a node arg from an initializer from initializer_names_to_preserve

* Fix CI failure

* update test

* Fix outer scope node args failure

* Use NodeArg* as the key of the std::set instead of string

* Minor updates
 2021-10-01 11:44:26 -07:00
Yulong Wang
8adb9ab85a
fix CodeQL warning for path-injection (#9243) 2021-10-01 11:32:00 -07:00
baijumeswani
45399d5ace
Remove TORCH_WARN to avoid torch string related operations that take up time (#9238) 2021-10-01 13:56:04 -04:00
Tang, Cheng
be4d887439
Fix ONNX exporter call with latest API for ORTrainer (#9228) 
* update the exporter call with latest api in orttrainer

* use official export api instead of the private call
 2021-10-01 13:49:55 -04:00
Yulong Wang
448325b254
[js/web] name ort web for consistency (#9240) 2021-09-30 22:53:26 -07:00
Tracy Sharpe
c23a216900
MLAS: fix AVXVNNI+Linux qgemv kernel (#9234) 2021-09-30 21:24:18 -07:00
Yulong Wang
e2d779246a
[wasm] remove deprecated prefix 'EXTRA_' in emcc flags (#9211) 2021-09-30 16:02:24 -07:00
Sheil Kumar
c6cb49c5a1
DirectML.dll load fails when executable path contains Non-English characters (#9229) 
* enable unicode dml

* add wide string L prefix

* Add Fail Fast back

Co-authored-by: Sheil Kumar <sheilk@microsoft.com>
 2021-09-30 15:16:57 -07:00
Yulong Wang
634bb5ede0
fix CodeQL warning 'Remote property injection' (#9224) 2021-09-30 13:45:22 -07:00
Yulong Wang
8c57d51928
support WebAssembly SIMD for qgemm (#9191) 
* support WebAssembly SIMD for qgemm

* remove '--experimental-wasm-bulk-memory' for test
 2021-09-30 12:40:56 -07:00
G. Ramalingam
e79be39081
LayerNormGrad function body and LayerNorm inference/body fix (#9160) 
* Add function body for LayerNormGrad

* Fix LayerNorm schema for multiple normalization dims
 2021-09-30 12:03:08 -07:00
Changming Sun
e1b84eefcc Revert "Revert "linux trt package pipeline (#7537)"" 
This reverts commit b606005858.
 2021-09-30 11:39:23 -07:00
Edward Chen
5326397a6a
[iOS] Facilitate usage of pods with custom builds (#9216) 
Refactor iOS framework build/pod package creation into a separate script that can be used with custom builds.
Add documentation.
 2021-09-30 08:44:00 -07:00
Thiago Crepaldi
ceb51dda4a
Support external torch cpp extensions on ORTModule (#9223) 2021-09-30 10:37:35 -04:00
RandySheriffH
ffca0b777b
Patching cuda profiler with enhancements (#9214) 2021-09-29 21:02:09 -07:00
Scott McKay
4a1b386f7c
#9182 removed the --is_store_build option but one place where that was used was missed. (#9219) 
This should fix the relevant packaging pipelines.
 2021-09-29 09:28:31 -07:00
satyajandhyala
278928a102
Added a test case for python gradient builder. (#9207) 
* Register Cos operator gradient using ORTModule's register_gradient and compare gradient against PyTorch.
 2021-09-29 09:24:12 -07:00
stevenlix
4f10024868
Fix shape inference issue in Gather op (#9147) 
* add initializer checker for Gather with 1D input

* Check if indices value exists

* Update symbolic_shape_infer.py

* add unit test

* Update symbolic_shape_infer.py

* Update symbolic_shape_infer.py
 2021-09-28 22:46:12 -07:00
Changming Sun
b606005858 Revert "linux trt package pipeline (#7537)" 
This reverts commit faea7a222d.
 2021-09-28 19:09:04 -07:00
RandySheriffH
058108bef9
Execution Provider Profiler (#8406) 
* implement cuda provider

* define profiler common

* call start after register

* add memcpy event

* add cuda correlation

* format code

* add cupti to test path

* switch to CUpti_ActivityKernel3

* reset cupti path

* fix test case

* fix trt pipeline

* add namespace

* format code

* exclude training from testing

* remove mutex
 2021-09-28 13:59:52 -07:00
Suffian Khan
6f580f07de
Switch AMD CI pipeline to use environment image from onnxruntimecibuildenvironment (#9206) 
* shift docker image reference for amd ci pipeline

* fix service endpoint

* reduce perf tolerance
 2021-09-28 13:06:16 -07:00
Changming Sun
1104e8d3e5
Linux Anybuild build pipeline (#9091) 2021-09-28 11:22:27 -07:00
ytaous
d3f859fe30
Dropout Vectorized Kernel (#9157) 
* vectorized kernel

* fix build

* re-calibrate expected loss

* fix build

* re-calibrate convergence results

* more re-calibrate on loss

* divide kernels

* adress comments

* more calibration

* calibration

* per comments

* enable sync

Co-authored-by: Ethan Tao <ettao@OrtTrainingDev4.af05slrtruoetgaxwwjv5nsq5e.px.internal.cloudapp.net>
 2021-09-27 17:19:12 -07:00
Wei-Sheng Chin
1b0816859f
Only wrap sub-modules which can be wrapped as ORTModule (#9021) 2021-09-27 17:18:22 -07:00