Skip to content

Commit

Permalink
ORT 1.14.0 release -- cherry pick round2 (#14573)
Browse files Browse the repository at this point in the history
### Description
<!-- Describe your changes. -->
Second round cherry pick, total 13 PRs, as below. Please check here for
[Here](https://github.com/microsoft/onnxruntime/issues?q=label%3Arelease%3A1.14+sort%3Aupdated-asc+is%3Aclosed+label%3Atriage%3Aapproved)
for the total list.

<html xmlns:v="urn:schemas-microsoft-com:vml"
xmlns:o="urn:schemas-microsoft-com:office:office"
xmlns:x="urn:schemas-microsoft-com:office:excel"
xmlns="http://www.w3.org/TR/REC-html40">

<head>

<meta name=ProgId content=Excel.Sheet>
<meta name=Generator content="Microsoft Excel 15">
<link id=Main-File rel=Main-File

href="file:///C:/Users/ruiren/AppData/Local/Temp/msohtmlclip1/01/clip.htm">
<link rel=File-List

href="file:///C:/Users/ruiren/AppData/Local/Temp/msohtmlclip1/01/clip_filelist.xml">
<style>
<!--table
	{mso-displayed-decimal-separator:"\.";
	mso-displayed-thousand-separator:"\,";}
@page
	{margin:.75in .7in .75in .7in;
	mso-header-margin:.3in;
	mso-footer-margin:.3in;}
tr
	{mso-height-source:auto;}
col
	{mso-width-source:auto;}
br
	{mso-data-placement:same-cell;}
td
	{padding-top:1px;
	padding-right:1px;
	padding-left:1px;
	mso-ignore:padding;
	color:black;
	font-size:11.0pt;
	font-weight:400;
	font-style:normal;
	text-decoration:none;
	font-family:Calibri, sans-serif;
	mso-font-charset:0;
	mso-number-format:General;
	text-align:general;
	vertical-align:bottom;
	border:none;
	mso-background-source:auto;
	mso-pattern:auto;
	mso-protection:locked visible;
	white-space:nowrap;
	mso-rotate:0;}
.xl65
	{text-align:center;}
.xl66
	{color:windowtext;
	text-align:center;
	border:.5pt solid windowtext;}
.xl67
	{text-align:center;
	border:.5pt solid windowtext;}
.xl68
	{text-align:center;
	border:.5pt solid windowtext;
	background:white;
	mso-pattern:black none;}
-->
</style>
</head>

<body link="#0563C1" vlink="#954F72">



Date | PR | # | Commit # | Short #
-- | -- | -- | -- | --
1 | Fix unused variable for CUDA EP builds with USE_FLASH_ATTENTION off
| 14404 | 85d7e9c | 85d7e9c
2 | UNet fusion and fp16 conversion for stable diffusion | 14248 |
a95fcb4 | a95fcb4
3 | upgrade protobuf to 3.20.2 and onnx to 1.13 | 14279 |
80f807c | 80f807c
4 | Include python training apis when enable_training is enabled | 14485
| d06ad94 | d06ad94
5 | Including support for Deepspeed 0.8.0 | 14506 |
6fa4555 | 6fa4555
6 | change deepspeed version in warning from 0.7.3 to 0.8.0 | 14527 |
3d388a1 | 3d388a1
7 | Do not fuse DQ+Node+Q if DQ produces graph output | 14509 |
d9e675a | d9e675a
8 | upgrade EsrpCodeSigning from v1 to v2 | 14531 |
0578eef | 0578eef
9 | Fix python packaging pipeline | 14533 |
7954976 | 7954976
10 | Specify deps in deps.txt and manifest | 14530 |
01cafe8 | 01cafe8
11 | Fix Gather to Split optimizer | 14478 |
0bcca7a | 0bcca7a
12 | Stable Diffusion CUDA Optimizations | 14428 |
a6c5ba0 | a6c5ba0
13 | Fix sharing scalar bug | 14544 |
c6c1103 | c6c1103



</body>

</html>


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

Second round cherry-pick for ORT 1.14.0 release.

---------

Co-authored-by: Adrian Lizarraga <[email protected]>
Co-authored-by: Tianlei Wu <[email protected]>
Co-authored-by: Yi Zhang <[email protected]>
Co-authored-by: Baiju Meswani <[email protected]>
Co-authored-by: Abhishek Jindal <[email protected]>
Co-authored-by: Yufeng Li <[email protected]>
Co-authored-by: Yulong Wang <[email protected]>
Co-authored-by: RandySheriffH <[email protected]>
Co-authored-by: Randy Shuai <[email protected]>
Co-authored-by: Xavier Dupré <[email protected]>
Co-authored-by: pengwa <[email protected]>
  • Loading branch information
12 people authored Feb 7, 2023
1 parent 1a48099 commit 5ae597d
Show file tree
Hide file tree
Showing 77 changed files with 5,068 additions and 427 deletions.
576 changes: 576 additions & 0 deletions ThirdPartyNotices.txt

Large diffs are not rendered by default.

97 changes: 94 additions & 3 deletions cgmanifests/generated/cgmanifest.json
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,7 @@
"component": {
"type": "git",
"git": {
"commitHash": "5a5f8a5935762397aa68429b5493084ff970f774",
"commitHash": "9b7bca2a723ff94edcd007d93b5d0cf1838591dc",
"repositoryUrl": "https://github.com/onnx/onnx.git"
},
"comments": "git submodule at cmake/external/onnx"
Expand All @@ -132,7 +132,7 @@
"component": {
"type": "git",
"git": {
"commitHash": "a902b39270841beafc307dfa709610aa1cac2f06",
"commitHash": "a20c65f2cd549445fda907f7b83894c8eb7427d6",
"repositoryUrl": "https://github.com/protocolbuffers/protobuf.git"
},
"comments": "git submodule at cmake/external/protobuf"
Expand Down Expand Up @@ -282,7 +282,7 @@
"component": {
"type": "git",
"git": {
"commitHash": "f412df7a2b64421e1f1d61fde6055a6ea288e8f5",
"commitHash": "28cf67e5b64c704cad993c71f29a24e781bee544",
"repositoryUrl": "https://github.com/microsoft/mimalloc.git"
},
"comments": "mimalloc"
Expand Down Expand Up @@ -328,6 +328,16 @@
"comments": "psimd"
}
},
{
"component": {
"type": "git",
"git": {
"commitHash": "a20c65f2cd549445fda907f7b83894c8eb7427d6",
"repositoryUrl": "https://github.com/protocolbuffers/protobuf.git"
},
"comments": "protobuf"
}
},
{
"component": {
"type": "git",
Expand Down Expand Up @@ -397,6 +407,87 @@
},
"comments": "cutlass"
}
},
{
"component": {
"type": "git",
"git": {
"commitHash": "6f7ffeb18f99796233b958aaaf14ec7bd4fb64b2",
"repositoryUrl": "https://github.com/microsoft/vcpkg.git"
},
"comments": "vcpkg"
}
},
{
"component": {
"type": "git",
"git": {
"commitHash": "19cc035b6c6f2283573d29c7ea7f7d675cf750ce",
"repositoryUrl": "https://github.com/openssl/openssl.git"
},
"comments": "openssl"
}
},
{
"component": {
"type": "git",
"git": {
"commitHash": "f54b0e47a08782a6131cc3d60f94d038fa6e0a51",
"repositoryUrl": "https://github.com/Tencent/rapidjson.git"
},
"comments": "rapidjson"
}
},
{
"component": {
"type": "git",
"git": {
"commitHash": "da041154c6bac1a4aa98254a7d6819059e8ac0b0",
"repositoryUrl": "https://github.com/boostorg/boost.git"
},
"comments": "boost"
}
},
{
"component": {
"type": "git",
"git": {
"commitHash": "9a6546658657dbeb23245117b57f4e6cf6cdc3e6",
"repositoryUrl": "https://github.com/libb64/libb64.git"
},
"comments": "b64"
}
},
{
"component": {
"type": "git",
"git": {
"commitHash": "75a84807a019bf4961faf713df9d748f0fc83b47",
"repositoryUrl": "https://github.com/triton-inference-server/server.git"
},
"comments": "triton server"
}
},
{
"component": {
"type": "git",
"git": {
"commitHash": "3712ec3f0426f7132d3759b84683d7d11e9ba683",
"repositoryUrl": "https://github.com/triton-inference-server/client.git"
},
"comments": "triton client"
}
},
{
"Component": {
"Type": "other",
"other": {
"Name": "pthread",
"Version": "3.0.0",
"DownloadUrl": "https://sourceforge.net/projects/pthreads4w/files/pthreads4w-code-v3.0.0.zip"
},
"comments": "posix pthread library"
}
}
]
}
15 changes: 12 additions & 3 deletions cmake/deps.txt
Original file line number Diff line number Diff line change
Expand Up @@ -21,12 +21,12 @@ googlexnnpack;https://github.com/google/XNNPACK/archive/003c580e696a774afdc98499
json;https://github.com/nlohmann/json/archive/refs/tags/v3.10.5.zip;f257f8dc27c5b8c085dc887b40cddd18ae1f725c
microsoft_gsl;https://github.com/microsoft/GSL/archive/refs/tags/v4.0.0.zip;cf368104cd22a87b4dd0c80228919bb2df3e2a14
microsoft_wil;https://github.com/microsoft/wil/archive/5f4caba4e7a9017816e47becdd918fcc872039ba.zip;fd119887d0d17c37adf1fc227b054befa28158ad
mimalloc;https://github.com/microsoft/mimalloc/archive/refs/tags/v2.0.3.zip;e4f37b93b2da78a5816c2495603a4188d316214b
mimalloc;https://github.com/microsoft/mimalloc/archive/refs/tags/v2.0.9.zip;9d4205c93805b5525de57c6c7ed7f60e770ffdac
mp11;https://github.com/boostorg/mp11/archive/refs/tags/boost-1.79.0.zip;c8f04e378535ededbe5af52c8f969d2dedbe73d5
onnx;https://github.com/onnx/onnx/archive/1ba785612a79fe749aa1e478336e534743372639.zip;6c22c32fabafac81107186ea6bedb31741a3142d
onnx;https://github.com/onnx/onnx/archive/refs/tags/v1.13.0.zip;8dda5079cdb5a134b08b0c73f4592a6404fc2dc6
#use the commit where it's several commits after 8.5-GA branch (https://github.com/onnx/onnx-tensorrt/commit/369d6676423c2a6dbf4a5665c4b5010240d99d3c)
onnx_tensorrt;https://github.com/onnx/onnx-tensorrt/archive/369d6676423c2a6dbf4a5665c4b5010240d99d3c.zip;62119892edfb78689061790140c439b111491275
protobuf;https://github.com/protocolbuffers/protobuf/archive/refs/tags/v3.18.3.zip;b95bf7e9de9c2249b6c1f2ca556ace49999e90bd
protobuf;https://github.com/protocolbuffers/protobuf/archive/refs/tags/v3.20.2.zip;9f71dad95fb83438e88822a9969fc93773fd8c48
psimd;https://github.com/Maratyszcza/psimd/archive/072586a71b55b7f8c584153d223e95687148a900.zip;1f5454b01f06f9656b77e4a5e2e31d7422487013
pthreadpool;https://github.com/Maratyszcza/pthreadpool/archive/1787867f6183f056420e532eec640cba25efafea.zip;e43e80781560c5ab404a4da20f34d846f5f5d101
pybind11;https://github.com/pybind/pybind11/archive/refs/tags/v2.10.1.zip;769b6aa67a77f17a770960f604b727645b6f6a13
Expand All @@ -35,3 +35,12 @@ re2;https://github.com/google/re2/archive/refs/tags/2022-06-01.zip;aa77313b76e91
safeint;https://github.com/dcleblanc/SafeInt/archive/ff15c6ada150a5018c5ef2172401cb4529eac9c0.zip;913a4046e5274d329af2806cb53194f617d8c0ab
tensorboard;https://github.com/tensorflow/tensorboard/archive/373eb09e4c5d2b3cc2493f0949dc4be6b6a45e81.zip;67b833913605a4f3f499894ab11528a702c2b381
cutlass;https://github.com/NVIDIA/cutlass/archive/refs/tags/v2.11.0.zip;be70c559f07251ba7f33c789dba98872b444c10f
# below are deps introduced by triton client, might remove after 1.14 release
vcpkg;https://github.com/microsoft/vcpkg/archive/refs/tags/2022.11.14.zip;3f983141351af5db2d6c3ca965959845f27d5d51
openssl;https://github.com/openssl/openssl/archive/refs/tags/openssl-3.0.7.zip;dda8fc81308555410505eb4a9eab3e1da0436a1d
rapidjson;https://github.com/Tencent/rapidjson/archive/refs/tags/v1.1.0.zip;0fe7b4f7b83df4b3d517f4a202f3a383af7a0818
boost;https://github.com/boostorg/boost/archive/refs/tags/boost-1.81.0.zip;f6ab0da855f825b4eb1abd949967d01a4c5e4e1b
b64;https://github.com/libb64/libb64/archive/refs/tags/v2.0.0.1.zip;815b6d31d50d9e63df55b25ce555e7b787153c28
pthread;https://sourceforge.net/projects/pthreads4w/files/pthreads4w-code-v3.0.0.zip;3b9e417e4474c34542b76ad40529e396ac109fb4
triton;https://github.com/triton-inference-server/server/archive/refs/tags/v2.28.0.zip;4b305570aa1e889946e20e36050b6770e4108fee
# above are deps introduced by triton client, might remove after 1.14 release
2 changes: 1 addition & 1 deletion cmake/external/onnxruntime_external_deps.cmake
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ FetchContent_Declare(
URL_HASH SHA1=${DEP_SHA1_protobuf}
SOURCE_SUBDIR cmake
PATCH_COMMAND ${ONNXRUNTIME_PROTOBUF_PATCH_COMMAND}
FIND_PACKAGE_ARGS 3.18.0 NAMES Protobuf
FIND_PACKAGE_ARGS 3.20.2 NAMES Protobuf
)
set(protobuf_BUILD_TESTS OFF CACHE BOOL "Build protobuf tests" FORCE)
if (CMAKE_SYSTEM_NAME STREQUAL "Android")
Expand Down
2 changes: 1 addition & 1 deletion cmake/external/protobuf
Submodule protobuf updated 894 files
9 changes: 9 additions & 0 deletions cmake/onnxruntime_rocm_hipify.cmake
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,15 @@ set(contrib_ops_excluded_files
"bert/tensorrt_fused_multihead_attention/*"
"bert/transformer_common.h"
"bert/transformer_common.cc"
"diffusion/group_norm.h"
"diffusion/group_norm.cc"
"diffusion/group_norm_impl.cu"
"diffusion/group_norm_impl.h"
"diffusion/bias_split_gelu_impl.h"
"diffusion/bias_split_gelu_impl.cu"
"diffusion/bias_split_gelu.h"
"diffusion/bias_split_gelu.cc"
"diffusion/nhwc_conv.cc"
"math/complex_mul.cc"
"math/complex_mul.h"
"math/complex_mul_impl.cu"
Expand Down
2 changes: 1 addition & 1 deletion cmake/onnxruntime_unittests.cmake
Original file line number Diff line number Diff line change
Expand Up @@ -763,7 +763,7 @@ if (MSVC)
# The warning means the type of two integral values around a binary operator is narrow than their result.
# If we promote the two input values first, it could be more tolerant to integer overflow.
# However, this is test code. We are less concerned.
target_compile_options(onnxruntime_test_all PRIVATE "/wd26451")
target_compile_options(onnxruntime_test_all PRIVATE "/wd26451" "/wd4244")
else()
target_compile_options(onnxruntime_test_all PRIVATE "-Wno-parentheses")
endif()
Expand Down
38 changes: 36 additions & 2 deletions cmake/patches/onnx/onnx.patch
Original file line number Diff line number Diff line change
@@ -1,8 +1,16 @@
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 8e595855..789ec80a 100644
index 4dd56b6e..018da488 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -545,20 +545,9 @@ endif()
@@ -397,6 +397,7 @@ if (MSVC)
endif()
else()
# On non-Windows, hide all symbols we don't need
+ set(EXTRA_FLAGS "-Wno-unused-parameter")
set(ONNX_API_DEFINE "-DONNX_API=__attribute__\(\(__visibility__\(\"default\"\)\)\)")
set_target_properties(onnx_proto PROPERTIES CXX_VISIBILITY_PRESET hidden)
set_target_properties(onnx_proto PROPERTIES VISIBILITY_INLINES_HIDDEN 1)
@@ -548,20 +549,9 @@ endif()
if(MSVC)
target_compile_options(onnx_proto
PRIVATE /MP
Expand All @@ -23,3 +31,29 @@ index 8e595855..789ec80a 100644
${EXTRA_FLAGS})
if(ONNX_USE_PROTOBUF_SHARED_LIBS)
target_compile_options(onnx_proto
diff --git a/onnx/onnx_pb.h b/onnx/onnx_pb.h
index 0aab3e26..0f859267 100644
--- a/onnx/onnx_pb.h
+++ b/onnx/onnx_pb.h
@@ -47,10 +47,21 @@
#define ONNX_API ONNX_IMPORT
#endif

+// onnx/onnx-operators-ml.pb.h:1178:25: required from here
+// protobuf/src/google/protobuf/repeated_ptr_field.h:752:66: error: unused parameter ‘prototype’ [-Werror=unused-parameter]
+#if defined(__GNUC__)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wunused-parameter"
+#endif
+
#ifdef ONNX_ML
#include "onnx/onnx-ml.pb.h"
#else
#include "onnx/onnx.pb.h"
#endif

+#if defined(__GNUC__)
+#pragma GCC diagnostic pop
+#endif
+
#endif // ! ONNX_ONNX_PB_H
18 changes: 12 additions & 6 deletions cmake/patches/protobuf/protobuf_cmake.patch
Original file line number Diff line number Diff line change
@@ -1,25 +1,31 @@
diff --git a/cmake/CMakeLists.txt b/cmake/CMakeLists.txt
index 61a5c3ded..68d7c5598 100644
index ac92442a1..e930cbd2e 100644
--- a/cmake/CMakeLists.txt
+++ b/cmake/CMakeLists.txt
@@ -199,12 +199,8 @@ if (MSVC)
endif()
@@ -240,9 +240,7 @@ if (MSVC)
# MSVC warning suppressions
add_definitions(
- /wd4018 # 'expression' : signed/unsigned mismatch
/wd4065 # switch statement contains 'default' but no 'case' labels
- /wd4146 # unary minus operator applied to unsigned type, result still unsigned
- /wd4244 # 'conversion' conversion from 'type1' to 'type2', possible loss of data
/wd4251 # 'identifier' : class 'type' needs to have dll-interface to be used by clients of class 'type2'
- /wd4267 # 'var' : conversion from 'size_t' to 'type', possible loss of data
/wd4305 # 'identifier' : truncation from 'type1' to 'type2'
/wd4307 # 'operator' : integral constant overflow
/wd4309 # 'conversion' : truncation of constant value
@@ -212,7 +208,6 @@ if (MSVC)
@@ -250,7 +248,6 @@ if (MSVC)
/wd4355 # 'this' : used in base member initializer list
/wd4506 # no definition for inline function 'function'
/wd4800 # 'type' : forcing value to bool 'true' or 'false' (performance warning)
- /wd4996 # The compiler encountered a deprecated declaration.
)
# Allow big object
add_definitions(/bigobj)
@@ -272,6 +269,8 @@ if (MSVC)
endif()

configure_file(version.rc.in ${CMAKE_CURRENT_BINARY_DIR}/version.rc @ONLY)
+else (MSVC)
+ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-unused-parameter")
endif (MSVC)


Loading

0 comments on commit 5ae597d

Please sign in to comment.