Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1109 commits
Select commit Hold shift + click to select a range
60bfa7f
Update publish-python-apidocs.yml (#22655)
Oct 31, 2024
a2070bf
Fix input shape related compile logs for MIGraphX EP to be semantical…
sstamenk Oct 31, 2024
69fe58b
Fix formatting of DML EP files that was disturbed in an earlier PR. (…
Oct 31, 2024
1b60209
[CUDA/ROCm/Migraphx] consolidate gpu data transfer (#22609)
tianleiwu Oct 31, 2024
55e0128
[DML EP] Cast to bool correctly, adding explicit clip after cast (#22…
dtang317 Oct 31, 2024
7b9db65
Fixed a minor bug in layout transformation for Resize (#21954)
Honry Oct 31, 2024
8e8b62b
Build CUDA and DML together (#22602)
mszhanyi Oct 31, 2024
f9bc24e
Add concurrency setting to codeql workflow (#22678)
Oct 31, 2024
c7ecc08
Revert "[WebNN] Fallback the node when its output doesn't have shape …
shiyi9801 Oct 31, 2024
9daf766
[CoreML] ML Program more ops (2/N) (#22480)
wejoncy Nov 1, 2024
8fbbf2f
[js/webgpu] Optimize MatMul with M = 1 (#22577)
qjia7 Nov 1, 2024
ba0bb43
Rework the native library usage so that a pre-built ORT native packag…
skottmckay Nov 1, 2024
f7cabf6
Use suggest-changes@v2 (#22667)
justinchuby Nov 1, 2024
62c3476
[WebNN] Remove some useless verbose logs (#22690)
Honry Nov 1, 2024
6d5e970
[CI] Set up proper permissions for linting workflow (#22696)
justinchuby Nov 2, 2024
d419df4
Fix too strict assert in onnx_quantizer.py (#22283)
xadupre Nov 2, 2024
2e4e221
Fix crash when running ORT under low integrity process like Edge wher…
ivberg Nov 2, 2024
4ffc1ff
DMMHA: add unit tests; fix CPU, CUDA kernel (#22567)
mindest Nov 2, 2024
120cb5a
[Doc] Add I/O binding example using onnx data type in python API summ…
tianleiwu Nov 2, 2024
ac6fe48
Adjust max chunk size to fix error limit check from DX12 for large re…
chrilaMSFT Nov 4, 2024
777fe79
[WebNN EP] Support Sign and CumSum operators (#22616)
miaobin Nov 4, 2024
c64459f
[WebNN] Don't skip scalar tensor registration (#22688)
Honry Nov 4, 2024
74adfc2
Nuget Windows AI Pipeline, Disable SDL Submodules. (#22711)
idiskyle Nov 4, 2024
5766833
[WebNN EP] Align QDQ ops with latest Chromium implementation (#22180)
Honry Nov 4, 2024
6c21ab7
[WebNN] Support SimplifiedLayerNormalization op (#22674)
Honry Nov 4, 2024
bd5dbf8
support WebGPU EP in Node.js binding (#22660)
fs-eire Nov 4, 2024
64d8e25
[js/webgpu] Optimize Gemm (#22706)
qjia7 Nov 4, 2024
66980e4
Refactor the cmake code that is related to delay loading (#22646)
Nov 5, 2024
33a2059
Remove webgpu ep in mobile packaging stages (#22725)
mszhanyi Nov 5, 2024
3711a65
Update DNNL CI python to 310 (#22691)
jchen351 Nov 5, 2024
db72096
Revert to err logging instead of LOGS_DEFAULT macro (#22720)
ivberg Nov 5, 2024
00461d1
Replace gsl::narrow with narrow in WebNN code (#22733)
sevagh Nov 5, 2024
d5b2730
[js/webgpu] Increase workgroupSize if only one workgroup is dispached…
qjia7 Nov 5, 2024
aa097a5
Fix GRU tests (#22716)
dtang317 Nov 5, 2024
0172462
support Qnn 2 28 (#22724)
HectorSVC Nov 5, 2024
0371e92
[webgpu] change default validation mode (#22730)
fs-eire Nov 6, 2024
deee480
Enable CUDA Python Test (#22717)
jchen351 Nov 6, 2024
742a0d3
[C# MauiModelTester] Fix icon name in Info.plist (#21666)
edgchen1 Nov 6, 2024
811231e
[js/webgpu] Destroy staging buffers aggressively during weights uploa…
Nov 6, 2024
1cb5cee
[WebNN EP] Fix issues with MLTensor caching (#22701)
egalli Nov 6, 2024
d993ec3
[CUDA] Fix NumericLimits (#22738)
tianleiwu Nov 6, 2024
ba22d78
[CUDA/ROCm] Conditionally support ArgMax and ArgMin for opset 12 and …
tianleiwu Nov 6, 2024
72186bb
[CUDA] Build nhwc ops by default (#22648)
tianleiwu Nov 6, 2024
2c1b17c
[Quant Tool] Introduce get_qdq_config() helper to get QDQ configurati…
adrianlizarraga Nov 6, 2024
4f6993d
[Quant Tool] Prevent int32 quantized bias from clipping by adjusting …
adrianlizarraga Nov 6, 2024
0221693
[Mobile] Add E2E BrowserStack tests for iOS tests (#22610)
carzh Nov 6, 2024
aa0cf1c
[Quant Tool] Update QDQ Pad, Slice, Softmax (#22676)
adrianlizarraga Nov 6, 2024
3b7a6eb
[TensorRT EP] support TensorRT 10.6-GA (#22644)
yf711 Nov 6, 2024
6a295eb
[JS/WebGPU] Creating devices with subgroup features enabled if possib…
jiangzhaoming Nov 7, 2024
a436b3a
[webgpu] fix indices type when it's 4D (#22758)
fs-eire Nov 7, 2024
f16036b
[DML EP] Prefer MatMulInteger over MatMulIntegerToFloat in case of (#…
AnaghaRaoAMD Nov 7, 2024
1936712
[AIX] Fix for AIX build break (#22745)
ranjitshs Nov 7, 2024
e7987a6
Replace reference to python 3.8 with python 3.10 (#22692)
jchen351 Nov 8, 2024
4d614e1
Fix build with GCC 11 (#22770)
cho-m Nov 8, 2024
d9b9168
WebGPU JSEP: Make shader code not depend on input broadcasting patter…
jiangzhaoming Nov 8, 2024
b5ee4ac
[js/webgpu] support GridSample operator (#22652)
xhcao Nov 8, 2024
020d52d
[Quant Tool] Add reduce_range option to get_qdq_config() (#22782)
adrianlizarraga Nov 8, 2024
a8539ec
Ignore all whitespace lint messages for cpplint (#22781)
justinchuby Nov 8, 2024
ef281f8
Add XNNPack build on Linux ARM64 and improve Linux CPU (#22773)
mszhanyi Nov 9, 2024
d3ad76b
[VitisAI] Cache node subgraph when necessary (#22073)
zz002 Nov 9, 2024
b9b1a03
[WebNN] QDQ's axis should be used for broadcasting (#22721)
Honry Nov 10, 2024
63cb532
[WebNN] Support steps >= 1 for slice operator (#22708)
shiyi9801 Nov 10, 2024
c9ed016
OVEP Dynamic WorkloadType support (#22779)
preetha-intel Nov 10, 2024
e8f1d73
Add Android QNN Browserstack test (#22434)
sheetalarkadam Nov 11, 2024
c5276ac
Revert "enable serialize prepacked weights into data file (#22256)" (…
yuslepukhin Nov 11, 2024
1f3b675
Fix MatMulBnFusion to exclude cases when tensors are not 2D tensors (…
xadupre Nov 11, 2024
885a7ac
Fix warning - LegacyKeyValueFormat: "ENV key=value" should be used in…
jchen351 Nov 11, 2024
b1e0930
Fix build for linux python wheel (#22801)
adrianlizarraga Nov 11, 2024
f7d1f0f
Reland "[WebNN] Fallback the node when its output doesn't have shape …
shiyi9801 Nov 12, 2024
0ad44d0
[Quant Tool] Flaky test due to Pad reflect bug (#22798)
adrianlizarraga Nov 12, 2024
cdc8db9
[WebNN] Fixed WebNN Module undefined issue (#22795)
Honry Nov 12, 2024
f0ac5e0
Update skip layer norm (#22719)
amarin16 Nov 12, 2024
9836ef1
register Identity and QLinearMatmul for opset21 (#22804)
dtang317 Nov 12, 2024
2b0f343
[MIGraphX EP] Add support for Gelu, BiasGelu, FastGelu operators (#22…
TedThemistokleous Nov 12, 2024
75a4458
Update all JDK version to 17 (#22786)
jchen351 Nov 12, 2024
fd5b1a1
Fix LARCH64 compile error (#22759)
junchao-loongson Nov 12, 2024
67f5be0
[WebNN EP] Support LRN operator (#22775)
miaobin Nov 12, 2024
05c8dc9
[js/webgpu] Optimize ConvTranspose (#22774)
qjia7 Nov 12, 2024
7e0dd9d
[js/webgpu] Optimize Expand (#22752)
qjia7 Nov 12, 2024
7fa6946
[ARM] MatMulNBits FP16 support - kernels only (#22806)
fajin-corp Nov 12, 2024
69a36eb
Revert Implement DML copy for Lora Adapters (#22814)
zhangxiang1993 Nov 12, 2024
bc2b1b5
Fix issue #22796 - a typo: (__GNUC__ > 9) -> (__GNUC__ > 10) (#22807)
liqunfu Nov 13, 2024
ff57ac4
[js/webgpu] Add scatterND (#22755)
axinging Nov 13, 2024
3adcf4d
[WebNN] Remove validation for coordinate_transformation_mode (#22811)
shiyi9801 Nov 13, 2024
fa4cbcd
[TensorRT EP] Add new provider option to exclude nodes from running o…
chilo-ms Nov 13, 2024
a9b62fa
Keep the model metadata on the generated EP context model (#22825)
HectorSVC Nov 13, 2024
a15381d
[WebNN EP] Fix issues of GRU operator (#22123)
miaobin Nov 13, 2024
6d7603f
Auto-generated baselines by 1ES Pipeline Templates (#22817)
microsoft-github-policy-service[bot] Nov 13, 2024
f423b73
Fix Linux python CUDA package pipeline (#22803)
jchen351 Nov 13, 2024
8268120
[WebNN] Fix MLTensorUsage is undefined issue (#22831)
Honry Nov 14, 2024
dd99e34
Enable ConvReplaceWithQLinear when using ACL (#22823)
MichaelTylerArm Nov 14, 2024
09c9843
[CUDA] stable diffusion benchmark allows IO binding for optimum (#22834)
tianleiwu Nov 14, 2024
5659d05
Fix Linux CI pipeline where ep was not provided for py-packaging-linu…
jchen351 Nov 14, 2024
12dfe28
Register groupnorm for opset 21 (#22830)
dtang317 Nov 14, 2024
c645bd2
Fix spellchecks from Optional Lint (#22802)
jchen351 Nov 14, 2024
c02b398
[ARM] MatMulNBits Fp16 support - API change only (#22826)
fajin-corp Nov 14, 2024
562ddce
Re-enable test symbolic shape infer (#22737)
yf711 Nov 14, 2024
0733733
[Quant tool] Handle input models with pre-quantized weights (#22633)
adrianlizarraga Nov 14, 2024
632a36a
Update Gradle version 8.7 and java version 17 within onnxruntime/java…
jchen351 Nov 15, 2024
ac9c135
Ovep develop 1.21 (#22824)
preetha-intel Nov 15, 2024
bbe7c87
Fix 1.20 cuda minimal build failure (#22751)
poweiw Nov 15, 2024
c73a3d1
[ARM] MatMulNBits fp16 support - connect kernels (#22856)
fajin-corp Nov 15, 2024
5928009
[WebNN EP] Support Einsum op (#19558)
peishenyan Nov 16, 2024
101ed10
Refactor SkipLayerNorm and handle beta properly (#22862)
liqunfu Nov 17, 2024
135d8b2
Fix CUDA/DML package exception caused by ENABLE_CUDA_NHWC_OPS (#22851)
mszhanyi Nov 18, 2024
02a0be3
Optimize Transpose around QLinearSoftmax (#22849)
yihonglyu Nov 18, 2024
c4f3742
Replace INFINITY by std::numeric_limits<float>::infinity() (#22868)
tianleiwu Nov 18, 2024
e597eae
[js/webgpu] Optimize transpose as reshape when suitable (#22870)
qjia7 Nov 18, 2024
497b06f
[QNN EP] QNN SDK 2.28.2 (#22844)
adrianlizarraga Nov 19, 2024
a0d36a5
Move C# doc Github Action to Windows (#22880)
Nov 19, 2024
56e4fda
[TensorRT EP] Revert "Add new provider option to exclude nodes from r…
chilo-ms Nov 19, 2024
0d00fc3
[mobile] Fix for mac-ios-packaging pipeline (#22879)
carzh Nov 19, 2024
8a06f13
[WebNN] Remove wasm.currentContext check (#22886)
Honry Nov 19, 2024
5b78712
[WebNN] Check split's output name (#22884)
Honry Nov 19, 2024
13346fd
Cleanup code (#22827)
Nov 19, 2024
af0303f
Simplify CPU allocator arena usage helper function, fix unit tests th…
edgchen1 Nov 19, 2024
712bee1
Fix Pipeline Timeout Issue (#22901)
idiskyle Nov 20, 2024
e430795
Fix MlasSgemmKernel: properly process more than 2 rows (#22125)
AlekseiNikiforovIBM Nov 21, 2024
a28246a
Revert "Update Gradle version 8.7 and java version 17 within onnxrunt…
mszhanyi Nov 21, 2024
369d7bf
Update the Docker image version (#22907)
jchen351 Nov 21, 2024
1e605be
bigmodel pipeline update cp38 to cp310 (#22793)
kailums Nov 21, 2024
55f0559
Update attention fusion to support SDPA pattern (#22629)
tianleiwu Nov 21, 2024
8d99b1a
reduce GQA test combinations (#22918)
tianleiwu Nov 21, 2024
f6e1d44
Add option to force generic algorithms on x86 (#22917)
AlekseiNikiforovIBM Nov 21, 2024
b1ccbe2
Minor update to onnxruntime_perf_test usage info for `-I` (#22810)
skottmckay Nov 22, 2024
c97dd6e
Update transformers test requirements (#22911)
tianleiwu Nov 22, 2024
a2ba3cb
Implementation of TreeEnsemble ai.onnx.ml==5 (#22333)
xadupre Nov 22, 2024
85751e7
Build DML in Windows GPU CI pipeline (#22869)
mszhanyi Nov 25, 2024
09d2ee6
Update pipeline status (#22924)
tianleiwu Nov 25, 2024
f80afeb
Override android qnn sdk version with pipeline param (#22895)
sheetalarkadam Nov 26, 2024
558ae86
[WebNN EP] Fix an issue of CumSum operator (#22936)
miaobin Nov 26, 2024
afbb539
[WebNN] Support negative steps for slice (#22871)
shiyi9801 Nov 26, 2024
8826e39
#22890 Fix profiling on empty Optional (#22891)
amancini-N Nov 26, 2024
487184f
[VSINPU] update crosscompiling patch (#22937)
chenfeiyue-cfy Nov 26, 2024
c284a68
[CoreML] Create EP by AppendExecutionProvider (#22675)
wejoncy Nov 27, 2024
fe749a8
[WebNN EP] Fixed bug in usage of Array.reduce() (#22944)
Honry Nov 27, 2024
b930b4a
Limit PipAuthenticate in Private Project now (#22954)
mszhanyi Nov 27, 2024
a24723d
[CoreML ] ML Program more operators support [3/N] (#22710)
wejoncy Nov 28, 2024
08abab0
[CPU] Fix mamtulnbits accuracy level (#22963)
fajin-corp Nov 28, 2024
42ecb05
[QNN] ReduceL2 Support (#22636)
Lafi7e Nov 28, 2024
1128882
Quantize Bias for Conv/Gemm on Quantized Model (#22889)
Lafi7e Nov 28, 2024
49a80df
Keep the model metadata on the generated EP context model (use bridge…
chilo-ms Dec 2, 2024
e234023
[TensorRT EP] Fix wrong input order when generating IndexedSubGraph (…
chilo-ms Dec 2, 2024
6c2ff5f
Refactor emulator start and stop functions for clarity and efficiency…
jchen351 Dec 2, 2024
e8bf46a
[WebGPU EP] Support GroupQueryAttention (#22658)
satyajandhyala Dec 2, 2024
8c52fa3
[VSINPU]Split/Pad and some element-wise OPs support (#22916)
xuke537 Dec 2, 2024
e2356a0
Use UTF8 string encoding in ORTSaveCodeAndDescriptionToError(). (#22982)
edgchen1 Dec 3, 2024
9ed0c7f
Redo "Update Gradle version 8.7 and java version 17 within onnxruntim…
jchen351 Dec 3, 2024
5c644d3
[WebGPU EP] Flatten implementation (#22964)
prathikr Dec 3, 2024
d3bc318
[js/node] fix CUDA artifact installation script for Linux/x64 (#22984)
fs-eire Dec 4, 2024
4497c97
Bump cross-spawn from 7.0.3 to 7.0.6 in /js/node (#22998)
dependabot[bot] Dec 4, 2024
e84b8e7
allow specify a custom local source path for Dawn (#22999)
fs-eire Dec 4, 2024
06526af
[js/webgpu] fix a bug in transpose shader (#22997)
fs-eire Dec 4, 2024
bd701e4
Bump cross-spawn from 7.0.3 to 7.0.6 in /js (#23003)
dependabot[bot] Dec 4, 2024
9b9f881
[TensorRT EP] Use TRT/CUDA/ORT version from runtime instead of build …
chilo-ms Dec 4, 2024
50b38ca
[js/web] update default export to include webgpu (#22754)
fs-eire Dec 4, 2024
a615bd6
Bump version of Dawn to 12a3b24c4 (#23002)
fs-eire Dec 4, 2024
c19617a
[js/webgpu] Add GatherND (#22847)
axinging Dec 4, 2024
fdf5ffe
[js/node] fix TypeScript declaration in onnxruntime-node (#23000)
fs-eire Dec 4, 2024
d0dde4f
[wasm/test] update packages versions (#23008)
fs-eire Dec 4, 2024
7b0fa40
fix requirements.txt path (#22946)
fs-eire Dec 4, 2024
fbe22fd
[ARM CPU] Fix flaky hqnbitgemm UT (#23010)
fajin-corp Dec 4, 2024
cacd97d
[WebNN] Improve the util function of creating WebNN constant MLOperan…
Honry Dec 4, 2024
3975e79
Bump axios from 1.6.1 to 1.7.9 in /js/node (#23009)
dependabot[bot] Dec 4, 2024
3234487
[js] remove more unused training types (#22753)
fs-eire Dec 5, 2024
f340b3c
Adding DML to python cuda package (#22606)
jchen351 Dec 5, 2024
1c79a4c
[js/common] use TS type inference to eliminate `unknown` (#23012)
fs-eire Dec 5, 2024
6ed77cc
Deprecate macos-12 (#23017)
mszhanyi Dec 5, 2024
d27fecd
Bump cross-spawn from 6.0.5 to 6.0.6 in /js/web (#23019)
dependabot[bot] Dec 5, 2024
401d16c
Enable QNN HTP spill fill buffer setting to save RAM usage. (#22853)
HectorSVC Dec 6, 2024
bd5a759
[ARM CPU] Add rotary embedding fp16 kernel (#23013)
fajin-corp Dec 6, 2024
f5293d2
Update Intel Thread Counts (#22894)
A-Satti Dec 6, 2024
6d9636f
[WebNN] Allow ops to handle ignoring an empty tensor as input (#22972)
Honry Dec 7, 2024
22ae97c
[webgpu] Add Alias def for Flatten (#23038)
fs-eire Dec 9, 2024
2f2c73b
Miscellaneous cleanups (#23048)
skottmckay Dec 9, 2024
8f3384b
Fix BeamSearch T5 if initializers are on outer scope (#23044)
amancini-N Dec 9, 2024
e12421b
[CoreML] more performace flag (#22975)
wejoncy Dec 10, 2024
708ee85
Reduce default logger usage (#23030)
skottmckay Dec 10, 2024
b14b4ec
Restore Qspectre flag (#23060)
A-Satti Dec 10, 2024
5f7b9d0
Upgrade gradle to 8.7 (#23016)
jchen351 Dec 10, 2024
bf4d3e1
Update vcpkg.json - lock flatbuffer version (#23046)
mc-nv Dec 10, 2024
defcc4f
[webgpu] Optimize Expand (#23052)
qjia7 Dec 10, 2024
fa6ad20
Minor updates to onnxruntime_java.cmake (#23068)
edgchen1 Dec 10, 2024
02f0af0
[WebNN] Improve data type check of slice op (#22988)
shiyi9801 Dec 10, 2024
d8de3c4
[CUDA EP] Fix BeamSearch on T5 with sequence_as_input_ids (#20667) (#…
amancini-N Dec 11, 2024
8800830
Implement 2d tiled matmulnbits specialized for prefill (#23058)
sushraja-msft Dec 11, 2024
e605870
[js/web] Update API for `ort.env.webgpu` (#23026)
fs-eire Dec 11, 2024
ebb968d
disable the EP context embed model by default in session option (#23070)
HectorSVC Dec 12, 2024
1f88284
OVEP 1.21.0 Development Updates (#23080)
ankitm3k Dec 12, 2024
890a719
Remove deprecated static from Eigen that contributes to size increase…
yuslepukhin Dec 12, 2024
01539ee
[js/webgpu] fix Conv2DMatMul shader's out-of-bound read (#23085)
fs-eire Dec 12, 2024
f43f40f
Backward compatible with old QNN version (#23095)
HectorSVC Dec 13, 2024
2a36fd4
Fix the ctx_gen tool to make sure all generated ctx.onnx have max_siz…
HectorSVC Dec 13, 2024
62e7e24
Add attrProto.release_s interface (#22977)
danyue333 Dec 13, 2024
3a0b958
add 2 CMake build options of Dawn (#23096)
fs-eire Dec 14, 2024
2ff66b8
Fix a deadlock bug in EigenNonBlockingThreadPool.h (#23098)
Dec 16, 2024
a4eb8f2
[VitisAI] Add profiler interface for vitisai (#23032)
tianfang-fafafa Dec 16, 2024
ae97068
Fix Pybind memory leak (#23105)
yuslepukhin Dec 16, 2024
9115682
[js/webgpu] disable failed tests temporarily (#23127)
fs-eire Dec 16, 2024
0981bbf
[webgpu] Optimize matmulnbits with M > 1 (#23102)
qjia7 Dec 17, 2024
5afab78
Update python version metadata (remove 3.7, 3.8, 3.9; add 3.13). (#23…
tianleiwu Dec 17, 2024
54edb43
[WebNN] Fixes MLTensor caching across different contexts (#23100)
egalli Dec 17, 2024
a5b60ec
[WebNN] Add limit to QDQ ops (#23076)
Honry Dec 17, 2024
e76bd2f
Update CODEOWNERS: remove onnxruntime-es (#21677)
Dec 17, 2024
5d7030e
Revert DML pipeline changes (#23135)
Dec 18, 2024
31e6e10
gather elements webgpu implementation (#23137)
prathikr Dec 19, 2024
ae6dcc8
Revert "[js/webgpu] disable failed tests temporarily (#23127)" (#23130)
fs-eire Dec 19, 2024
7807350
[nodejs binding] Fix building in latest clang (#23146)
fs-eire Dec 19, 2024
8680244
Fix delay load for WebGPU EP and DML EP (#23111)
fs-eire Dec 19, 2024
a3bb3f1
[TensorRT EP] New CIs to test TRT+minimal CUDA build (#23028)
yf711 Dec 19, 2024
d9d07ad
[TensorRT EP] support TensorRT 10.7-GA (#23011)
yf711 Dec 19, 2024
b4a6a0d
[WebGPU EP] allows GPUDevice to be released after use (#23144)
fs-eire Dec 19, 2024
7c782f6
[webgpu] Always use tile matmulnbits for block_size = 32 (#23140)
qjia7 Dec 20, 2024
4aca8f3
[Bug Fix] Missing CustomOp SchemaRegister when generator EPContext ON…
mingyueliuh Dec 20, 2024
29bccad
[webgpu] fix compiling error (#23139)
xhcao Dec 20, 2024
00b262d
Implement pre-packed blobs serialization on disk and their memory map…
yuslepukhin Dec 20, 2024
fcc34da
Fix a tiny problem in winml.cmake (#23173)
Dec 20, 2024
6806174
fix webgpu delay load test (#23157)
fs-eire Dec 20, 2024
ebdbbb7
[VitisAI] Int4 support (#22850)
BoarQing Dec 21, 2024
c6ba7ed
Enable pointer-generator T5 models in BeamSearch (#23134)
amancini-N Dec 23, 2024
81cd6ea
[QNN EP] Fix multithread sync bug in ETW callback (#23156)
adrianlizarraga Dec 23, 2024
a9a881c
Integrate onnx 1.17.0 (#21897)
liqunfu Dec 24, 2024
2d05c4b
[WebNN] Support SkipSimplifiedLayerNormalization op (#23151)
Honry Dec 24, 2024
8687011
[CoreML] support coreml model cache (#23065)
wejoncy Dec 31, 2024
69bb53d
Enable delay loading hooker for python packages (#23227)
Dec 31, 2024
2116fd1
Update onnxruntime_c_api.h to work with MinGW (#23169)
jcelerier Dec 31, 2024
afd3e81
Remove PostBuildCleanup (#23233)
Dec 31, 2024
0b87bcc
[CUDA] Make cubins const (#23225)
mityada Jan 1, 2025
a3833a5
[js/webgpu] validate transpose perm if specified (#23197)
xhcao Jan 1, 2025
bc91f5c
[TensorRT EP] Fix to build ORT on legacy TRT8.5 (#23215)
yf711 Jan 2, 2025
aedb49b
[VitisAI] change all support tensor type from ir 9 to ir 10 (#23204)
BoarQing Jan 2, 2025
5d692b0
Merge web machine pools (#23243)
Jan 3, 2025
5c2e60c
[js/node] update install script to allow use proxy (#23242)
fs-eire Jan 3, 2025
4247153
[webgpu] Add kernel type to profile info (#23167)
qjia7 Jan 3, 2025
b7ef81a
Move Linux GPU CI pipeline to A10 (#23235)
Jan 5, 2025
2a16ad0
[js/node] add proxy agent support for onnxruntime-node install script…
jnzw Jan 5, 2025
21b4d2a
fix pipeline build-perf-test-binaries (#23255)
fs-eire Jan 6, 2025
c53c9ca
[js] update mocha to v11.0.1 (#23254)
fs-eire Jan 6, 2025
c6cbda3
Update Python-Cuda-Publishing-Pipeline (#23253)
Jan 6, 2025
704523c
[build] Be compatible with the latest protobuf (#23260)
Jan 6, 2025
655b3ef
Separating result processor out from profiler.py (#23251)
jchen351 Jan 7, 2025
519fae0
[WebNN] Fix bug in SkipSimplifiedLayerNormalization (#23236)
Honry Jan 7, 2025
4883ec5
[webgpu] Use override shape in shader key (#23188)
qjia7 Jan 7, 2025
4b0cee3
fix: Pad/AveragePool fusion (#23190)
mayeut Jan 7, 2025
d8e8d4f
disable scatternd op for jsep (#23277)
prathikr Jan 8, 2025
c75681a
Address CodeQL security issues on comparison of different types (#23276)
wonchung-microsoft Jan 8, 2025
ff0ab0a
Quantize Weight for Gemm/Conv on Quantized Model (#22969)
Lafi7e Jan 8, 2025
34d70f5
[QNN] MatMul Op Builder to Handle All Cases of ONNX's MatMul (#22639)
Lafi7e Jan 8, 2025
da35cce
Add a temporary path to RN 0.69.3 to update the boost url (#23281)
jchen351 Jan 8, 2025
5b9c968
Correct ONNX and Protobuf version in vcpkg build (#23285)
luncliff Jan 8, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
The diff you're trying to view is too large. We only load the first 3000 changed files.
77 changes: 77 additions & 0 deletions .config/1espt/PipelineAutobaseliningConfig.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,77 @@
## DO NOT MODIFY THIS FILE MANUALLY. This is part of auto-baselining from 1ES Pipeline Templates. Go to [https://aka.ms/1espt-autobaselining] for more details.

pipelines:
1624:
retail:
source:
credscan:
lastModifiedDate: 2024-10-25
policheck:
lastModifiedDate: 2024-10-25
eslint:
lastModifiedDate: 2024-10-25
psscriptanalyzer:
lastModifiedDate: 2024-10-25
armory:
lastModifiedDate: 2024-10-25
usedNonDefaultBranch: true
1299:
retail:
source:
credscan:
lastModifiedDate: 2024-10-25
eslint:
lastModifiedDate: 2024-10-25
psscriptanalyzer:
lastModifiedDate: 2024-10-25
armory:
lastModifiedDate: 2024-10-25
policheck:
lastModifiedDate: 2024-10-29
binary:
credscan:
lastModifiedDate: 2024-10-25
binskim:
lastModifiedDate: 2024-10-25
spotbugs:
lastModifiedDate: 2024-10-25
1625:
retail:
source:
credscan:
lastModifiedDate: 2024-11-05
policheck:
lastModifiedDate: 2024-11-05
eslint:
lastModifiedDate: 2024-11-05
psscriptanalyzer:
lastModifiedDate: 2024-11-05
armory:
lastModifiedDate: 2024-11-05
binary:
credscan:
lastModifiedDate: 2024-11-13
binskim:
lastModifiedDate: 2024-11-13
spotbugs:
lastModifiedDate: 2024-11-13
1626:
retail:
source:
credscan:
lastModifiedDate: 2024-11-13
policheck:
lastModifiedDate: 2024-11-13
eslint:
lastModifiedDate: 2024-11-13
psscriptanalyzer:
lastModifiedDate: 2024-11-13
armory:
lastModifiedDate: 2024-11-13
binary:
credscan:
lastModifiedDate: 2024-11-13
binskim:
lastModifiedDate: 2024-11-13
spotbugs:
lastModifiedDate: 2024-11-13
43 changes: 43 additions & 0 deletions .config/guardian/.gdnbaselines
Original file line number Diff line number Diff line change
@@ -0,0 +1,43 @@
{
"properties": {
"helpUri": "https://eng.ms/docs/microsoft-security/security/azure-security/cloudai-security-fundamentals-engineering/security-integration/guardian-wiki/microsoft-guardian/general/baselines"
},
"version": "1.0.0",
"baselines": {
"default": {
"name": "default",
"createdDate": "2024-11-13 00:40:35Z",
"lastUpdatedDate": "2024-11-13 00:40:35Z"
}
},
"results": {
"48f03e2797fc40ecea50f878a0268947c7e13db1b2fa51aa3981246844fc4c68": {
"signature": "48f03e2797fc40ecea50f878a0268947c7e13db1b2fa51aa3981246844fc4c68",
"alternativeSignatures": [],
"target": "ScanTelemetry_20241113003616898.json",
"line": 1,
"memberOf": [
"default"
],
"tool": "credscan",
"ruleId": "CSCAN-AZURE0130",
"createdDate": "2024-11-13 00:40:35Z",
"expirationDate": "2025-05-02 01:29:47Z",
"justification": "This error is baselined with an expiration date of 180 days from 2024-11-13 01:29:47Z"
},
"9cb6eddb3f3e886ad06cae65f5886412ff0c5fb0b96d4e943e4efa237be617b1": {
"signature": "9cb6eddb3f3e886ad06cae65f5886412ff0c5fb0b96d4e943e4efa237be617b1",
"alternativeSignatures": [],
"target": "ScanTelemetry_20241113111547065.json",
"line": 1,
"memberOf": [
"default"
],
"tool": "credscan",
"ruleId": "CSCAN-AZURE0130",
"createdDate": "2024-11-13 11:20:17Z",
"expirationDate": "2025-05-02 11:55:15Z",
"justification": "This error is baselined with an expiration date of 180 days from 2024-11-13 11:55:15Z"
}
}
}
2 changes: 1 addition & 1 deletion .gitattributes
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# This sets the default behaviour, overriding core.autocrlf
# This sets the default behavior, overriding core.autocrlf
* text=auto

# All source files should have unix line-endings in the repository,
Expand Down
1 change: 1 addition & 0 deletions .github/ISSUE_TEMPLATE/05-performance.yml
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
name: Performance
description: issues related to performance
title: "[Performance] "
labels: ["performance"]
body:
- type: markdown
attributes:
Expand Down
7 changes: 7 additions & 0 deletions .github/codeql/codeql-config.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
name: "CodeQL config"
queries:
- uses: security-extended
- uses: security-and-quality
paths-ignore:
- tests
- build
31 changes: 18 additions & 13 deletions .github/labeler.yml
Original file line number Diff line number Diff line change
@@ -1,20 +1,25 @@
api:javascript: '/\bjavascript\b/i'
api:CSharp: '/(\bc\s*sharp\b|\bc#)/i'
api:java: '/\bjava\b/i'
api:javascript: '/\bjavascript\b/i'
ep:ACL: '/\bacl\b/i'
ep:ArmNN: '/\barmnn\b/i'
ep:CUDA: '/\bcuda\b/i'
ep:DML: '/(\bdirectml\b|\bdml\b)/i'
ep:MIGraphX: '/\bmigraphx\b/i'
ep:oneDNN: '/\bonednn\b/i'
ep:CANN: '/\bcann\b/i'
ep:CoreML: '/\bcore\s*ml\b/i'
ep:DML: '/(\bdirect\s*ml\b|\bdml\b)/i'
ep:MIGraphX: '/\bmi\s*graph\s*x\b/i'
ep:oneDNN: '/\bone\s*dnn\b/i'
ep:OpenVINO: '/\bopen\s*vino\b/i'
ep:RockchipNPU: '/\brockchip\b/i'
ep:QNN: '/\bqnn\b/i'
ep:RockchipNPU: '/\brockchip(?:npu)?\b/i'
ep:ROCm: '/\brocm\b/i'
ep:TensorRT: '/(\btensor\s*rt\b|\btrt\b)/i'
ep:SNPE: '/\bsnpe\b/i'
ep:tvm: '/\btvm\b/i'
ep:VitisAI: '/\bvitis(?:ai)?\b/i'
platform:jetson: '/\bjetson\b/i'
platform:mobile: '/(\bobj(?:ective)?-?c\b|\bnnapi\b|\bcore-?ml\b|\bmobile\b|\bandroid\b|\bios\b|\bxamarin\b|\bmaui\b)/i'
platform:web: '/(\bwebgl\b|\bweb-?gpu\b|\bwasm\b|\bonnxruntime-node\b|\bonnxruntime-web\b)/i'
platform:windows: '/(\bwindows\b|\bwinrt\b|\bwinml\b)/i'
model:transformer: '/(\bbert\b|\bgpt-?2\b|\bhugging-?face\b|\blong-?former\b|\bt5\b)/i'
quantization: '/(is this a quantized model\?\n\nYes|\bquantization\b)/i'
ep:WebGPU: '/\bwebgpu\b/i'
ep:WebNN: '/\bwebnn\b/i'
ep:Xnnpack: '/\bxnn\s*pack\b/i'
.NET: '/(\bdot\s*net\b|\bnuget\b|\.net\b)/i'
platform:jetson: '/(\bjetson\b|\bjetpack\b)/i'
platform:mobile: '/(\bobj(?:ective)?-?c\b|\bnnapi\b|\bmobile\b|\bandroid\b|\bios\b|\bxamarin\b|\bmaui\b)/i'
platform:web: '/(\bwebgl\b|\bweb-?gpu\b|\bwasm\b|\bonnxruntime-node\b|\bonnxruntime-web\b|\bonnxruntime-react-native\b|\bnpm\b|\btransformers\.js\b)/i'
model:transformer: '/\btransformers(?!\.js)\b/i'
4 changes: 4 additions & 0 deletions .github/title-only-labeler.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
ep:CUDA: '/\bcuda\b/i'
ep:TensorRT: '/(\btensor\s*rt\b|\btrt\b)/i'
platform:windows: '/(\bwindows\b|\bwinrt\b|\bwinml\b)/i'
quantization: '/(quant|\bqdq\b)/i'
2 changes: 1 addition & 1 deletion .github/workflows/cffconvert.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ on:
jobs:
validate:
name: "validate"
runs-on: ubuntu-latest
runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU"]
steps:
- name: Check out a copy of the repository
uses: actions/checkout@v4
Expand Down
11 changes: 10 additions & 1 deletion .github/workflows/codeql.yml
Original file line number Diff line number Diff line change
Expand Up @@ -15,10 +15,14 @@ on:
schedule:
- cron: '41 13 * * 0'

concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true

jobs:
analyze:
name: Analyze
runs-on: ubuntu-latest
runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU"]
permissions:
actions: read
contents: read
Expand Down Expand Up @@ -55,6 +59,11 @@ jobs:
java-version: '11'
distribution: 'microsoft'

- if: ${{ matrix.language == 'javascript' }}
uses: actions/setup-node@v4
with:
node-version: 20

# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
# If this step fails, then you should remove it and run the build manually (see below)
- if: ${{ matrix.language != 'cpp' }}
Expand Down
4 changes: 2 additions & 2 deletions .github/workflows/gradle-wrapper-validation.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ on: [push, pull_request]
jobs:
validation:
name: "Validation"
runs-on: ubuntu-latest
runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU"]
steps:
- uses: actions/checkout@v4
- uses: gradle/wrapper-validation-action@v3
- uses: gradle/actions/wrapper-validation@v4
2 changes: 1 addition & 1 deletion .github/workflows/labeler.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ permissions:

jobs:
triage:
runs-on: ubuntu-latest
runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU"]
steps:
- uses: github/issue-labeler@v3.4
with:
Expand Down
47 changes: 38 additions & 9 deletions .github/workflows/lint.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,10 @@ on:
- rel-*
pull_request:

concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.event_name == 'workflow_dispatch' }}
cancel-in-progress: true

jobs:
optional-lint:
name: Optional Lint
Expand All @@ -32,23 +36,29 @@ jobs:
lint-python-format:
# Required workflow
name: Python format
runs-on: ubuntu-latest
runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU"]
permissions:
contents: read
security-events: write
steps:
- uses: actions/checkout@v4
- name: Setup Python
uses: actions/setup-python@v5
with:
# Version range or exact version of Python to use, using SemVer's version range syntax. Reads from .python-version if unset.
# Use the version configured in target-version of [tool.black] section in pyproject.toml.
python-version: "3.10"
- name: Setup Rust
uses: actions-rs/toolchain@v1
with:
toolchain: stable
components: rustfmt
- name: Update PATH
run: |
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
- name: Install dependencies
run: |
python -m pip install -r requirements-dev.txt
python -m pip install lintrunner lintrunner-adapters
set -e -x
python -m pip install --user -r requirements-dev.txt
lintrunner init
- name: Run lintrunner on all files
run: |
Expand All @@ -73,12 +83,16 @@ jobs:
checkout_path: ${{ github.workspace }}

lint-cpp:
name: Lint C++
name: Optional Lint C++
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@master
- name: Update PATH
run: |
echo "$HOME/.local/bin" >> "$GITHUB_PATH"

- name: Install ninja
run: python -m pip install --upgrade ninja
run: python -m pip install --user --upgrade ninja
- name: Generate compile_commands.json
run: |
python tools/ci_build/build.py \
Expand All @@ -89,18 +103,33 @@ jobs:
- name: Generate ONNX protobuf files
run: cmake --build build/Debug --config Debug --target onnx_proto
- uses: reviewdog/action-cpplint@master
continue-on-error: true
with:
github_token: ${{ secrets.github_token }}
reporter: github-pr-check
level: warning
flags: --linelength=120 --exclude=java/src/main/native/*.c
level: info
flags: --linelength=120
--exclude=java/src/main/native/*.c
--exclude=onnxruntime/core/mlas/inc/*
--exclude=onnxruntime/core/mlas/lib/*
--exclude=onnxruntime/contrib_ops/cuda/bert/flash_attention/*
--exclude=build/Debug/*
--exclude=cmake/*
--exclude=csharp/test/*
--exclude=onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/GeneratedShaders/*
--exclude=orttraining/orttraining/test/*
--exclude=onnxruntime/test/*
--exclude=winml/*
filter: "-runtime/references"

lint-js:
name: Lint JavaScript
runs-on: ubuntu-latest
runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU"]
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: 20
- uses: reviewdog/action-eslint@v1
with:
reporter: github-pr-check
Expand Down
32 changes: 0 additions & 32 deletions .github/workflows/linux.yml

This file was deleted.

Loading