Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
243 commits
Select commit Hold shift + click to select a range
e85411a
Updated Internal CI (#581)
jatinwadhwa921 Dec 18, 2024
0d42af9
Updated Internal CI OV version (#594)
jatinwadhwa921 Feb 25, 2025
3dc24ef
Updated ov version in pipeline (#595)
jatinwadhwa921 Feb 27, 2025
9c2fee5
[OVEP] Fix for deprecated OV element type (#597)
jatinwadhwa921 Feb 28, 2025
17f4bc7
Merge branch 'master' into sync_msft_29_2_25
n1harika Feb 28, 2025
4bb577a
Merge pull request #600 from intel/sync_msft_29_2_25
ankitm3k Feb 28, 2025
60ee27a
Sahar/session option develop (#601)
sfatimar Feb 28, 2025
ec62bf3
Use absolute paths for libraries loaded with LOAD_WITH_ALTERED_SEARCH…
jnagi-intel Mar 4, 2025
bd32f51
Remove unintended model copies during compilation (#584)
ericcraw Mar 4, 2025
a6cdf62
Rebasing with msft commits (#607)
jatinwadhwa921 Mar 10, 2025
cdc209c
Revert "Rebasing with msft commits (#607)"
ankitm3k Mar 10, 2025
920ed58
Merge pull request #607
ankitm3k Mar 10, 2025
788fc78
Revert "Merge pull request #607"
jatinwadhwa921 Mar 10, 2025
a046532
Merge pull request #609 from intel/jatin_revert_msft_changes
ankitm3k Mar 10, 2025
ec98cce
Merge branch 'master' into syncing_msft_commits_3_10_25
jatinwadhwa921 Mar 10, 2025
73e0fea
Merge pull request #611 from intel/syncing_msft_commits_3_10_25
jatinwadhwa921 Mar 10, 2025
61b36ef
[OVEP] Fix for precision accuracy
jatinwadhwa921 Mar 5, 2025
ea13a05
Merge pull request #603 from intel/jatin_fix_precison_acc_issue
sfatimar Mar 11, 2025
7683e37
Refactor OVRTAllocator to return base pointer of remote tensor (#613)
ericcraw Mar 17, 2025
1788576
Commit Lint Errors fix (#606)
sfatimar Mar 18, 2025
23e17e2
fix quantizedLinear layer feeds into grapg output (#615)
saurabhkale17 Mar 18, 2025
91e64fe
Merge branch 'master' into sync_msft_18_3_25
jatinwadhwa921 Mar 18, 2025
6083601
Merge pull request #621 from intel/sync_msft_18_3_25
jatinwadhwa921 Mar 18, 2025
8b4a6d2
[OVEP] Fix for dumping the model in correct format (#616)
jatinwadhwa921 Mar 19, 2025
7269615
[OVEP] Added Cast and Resize to operators that handle zero-valued dim…
jatinwadhwa921 Mar 19, 2025
9ee95d1
Merge branch 'master' into sync_msft_20_3_25
jatinwadhwa921 Mar 20, 2025
2a24806
Merge pull request #624 from intel/sync_msft_20_3_25
jatinwadhwa921 Mar 21, 2025
c7ac5c8
Merge branch 'master' into sync_msft_25_3_25
jatinwadhwa921 Mar 25, 2025
2c61a3a
Merge pull request #627 from intel/sync_msft_25_3_25
jatinwadhwa921 Mar 26, 2025
e240695
[OVEP] Fix for Dynamic backend creation for NPU. (#622)
gupta-pallavi Mar 27, 2025
322a7e1
Remove unnecessary device queries (#620)
nproshun Mar 28, 2025
25912f7
Add support for parsing AUTO, HETERO and MULTI from json config (#605)
preetha-intel Apr 2, 2025
fbf43a9
Revert "[OVEP] Fix for Dynamic backend creation for NPU. (#622)" (#635)
gupta-pallavi Apr 3, 2025
2313d11
[OVEP] Fix for building OVEP without vcpkg flag (#637)
jatinwadhwa921 Apr 3, 2025
a9a3d10
Merge branch 'master' into sync_msft_4_4_25
jatinwadhwa921 Apr 4, 2025
0636815
Merge pull request #638 from intel/sync_msft_4_4_25
jatinwadhwa921 Apr 4, 2025
1e85f1d
[OVEP] Updated Documentation for python wheels (#640)
jatinwadhwa921 Apr 4, 2025
80dfee9
Device type refactoring (#630)
preetha-intel Apr 4, 2025
2e4d541
Enable adaptive stripping and eliminate dependency of weight sharing …
saurabhkale17 Apr 7, 2025
c0c347c
Add Config for Release build
saurabhkale17 Apr 8, 2025
8517c64
Merge branch 'master' into syncing_msft_8_4_25
saurabhkale17 Apr 8, 2025
b999a1b
Merge pull request #643 from intel/syncing_msft_8_4_25
jatinwadhwa921 Apr 8, 2025
a8527b9
Bug fix in provider key verification (#644)
preetha-intel Apr 8, 2025
4e63ef6
Fix the LUID check (#647)
preetha-intel Apr 10, 2025
f0216fd
Merge branch 'master' into sync_msft_10_4_25
jatinwadhwa921 Apr 10, 2025
a5e6e05
Merge pull request #649 from intel/sync_msft_10_4_25
jatinwadhwa921 Apr 10, 2025
6fc0ed0
Update OV version for Intel Internal CI
jatinwadhwa921 Apr 11, 2025
9294c4c
Merge pull request #652 from intel/jatin_update_int_ci_2025_1
ankitm3k Apr 11, 2025
c2558f3
[OVEP] Update ov version in ort (#653)
jatinwadhwa921 Apr 11, 2025
ad5f824
Removing support for internal ci(Intel Internal) (#662)
jatinwadhwa921 Apr 17, 2025
254bda0
Merge branch 'master' into sync_msft_17_4_25
jatinwadhwa921 Apr 17, 2025
21c7ab3
Merge pull request #663 from intel/sync_msft_17_4_25
jatinwadhwa921 Apr 17, 2025
4c0acd8
Support for triggering Internal Ci(Intel Internal) (#665)
jatinwadhwa921 Apr 21, 2025
7401335
incorporate requested changes for PR:24394 (#661)
saurabhkale17 Apr 21, 2025
269f6fe
Add support for session option ep.stop_context_sharing (#655)
javier-intel Apr 23, 2025
7451884
Merge branch 'master' into sync_msft_24_4_25
jatinwadhwa921 Apr 24, 2025
e59c069
Merge pull request #675 from intel/sync_msft_24_4_25
ankitm3k Apr 24, 2025
9ee331a
Revert "Add support for session option ep.stop_context_sharing (#655)…
ankitm3k Apr 24, 2025
a077c79
Release model proto after we have the serialized string to reduce pea…
intbf Apr 29, 2025
9dd6a1a
Merge branch 'master' into sync_msft_2_5_25
jatinwadhwa921 May 2, 2025
e354009
Merge pull request #683 from intel/sync_msft_2_5_25
jatinwadhwa921 May 2, 2025
8d2f3c4
add channel wise quantization option for QDQ, and opt for intel NPU (…
bopeng1234 May 14, 2025
76d3122
Don't include initializers in compute capability (#686)
ericcraw May 15, 2025
e6dd15b
Merge branch 'master' into sync_msft_16_5_25
jatinwadhwa921 May 16, 2025
080f66b
Merge pull request #692 from intel/sync_msft_16_5_25
ankitm3k May 16, 2025
8d57482
[OVEP] Fixed coverity issues (#693)
jatinwadhwa921 May 19, 2025
599cd25
[GPU] Enable qdq_stripping path for GPU (#694)
intbf May 23, 2025
1a22a57
Optimize CPU time spent in inference path (#682)
ericcraw May 26, 2025
b602f47
Support workload type for dynamic shaped models (#690)
preetha-intel May 26, 2025
ad5413d
Merge branch 'master' into sync_msft_2_6_25
jatinwadhwa921 Jun 2, 2025
be8fded
Merge pull request #699 from intel/sync_msft_2_6_25
ankitm3k Jun 2, 2025
be8f8be
Sahar/tdr failure (#698)
sfatimar Jun 5, 2025
660adfc
feat: ORT GenAI Stateful Compilation changes (#676)
ankitm3k Jun 5, 2025
5ec3c7e
OVEP unittest (#685)
vthaniel Jun 10, 2025
81c5f59
Merge branch 'master' into ovep-develop
ankitm3k Jun 13, 2025
f86768b
Merge pull request #708 from intel/sync_msft_13_6_25
ankitm3k Jun 13, 2025
ca06b7a
Support for bounded dynamic model (#701)
preetha-intel Jun 14, 2025
9b245a4
[OVEP] Fix for appropriate device not selected (#696)
jatinwadhwa921 Jun 16, 2025
409b224
Improve the condition for device=GPU and qdq stripping enabled (#705)
intbf Jun 16, 2025
cbef617
Optimize CPU time spent in inference path (continued) (#695)
ericcraw Jun 19, 2025
6d04a2e
feat: Enable EpContext OVIR Encapsulation (#704)
ankitm3k Jun 24, 2025
278f6a7
Add operator hardSwish into OVEP (#709)
Kotomi-Du Jun 25, 2025
90869ff
[CVS-169168] Change name of metadata file and add filepath validation…
javier-intel Jun 25, 2025
e141e2f
fix: Fix logic in OnnxToOvNetworkBindings for stateful models (#719)
RyanMetcalfeInt8 Jun 25, 2025
7176c12
Merge branch 'master' into sync_msft_25_6_25
ankitm3k Jun 25, 2025
a95ed23
Merge pull request #721 from intel/sync_msft_25_6_25
ankitm3k Jun 25, 2025
7f86fad
[OVEP] Fix UnsupportedOpMode logic for Reshape
mdvoretc-intel Jun 10, 2025
dfc8ff0
Fix metadata name when ep.context_file_path is not provided (#722)
javier-intel Jun 27, 2025
0c1fcfd
EPCtx changes for dynamic model with reshape_input provider optional …
gupta-pallavi Jul 1, 2025
f3672df
Merge branch 'master' into ovep-develop
ankitm3k Jul 2, 2025
c3284bc
Merge pull request #724 from intel/sync_msft_2_7_27
ankitm3k Jul 2, 2025
13e7792
fix: enable test & lint fixes (#725)
ankitm3k Jul 2, 2025
80daa9b
Reduce the peak memory even with CPU fallback by moving the fallback …
preetha-intel Jul 2, 2025
e2ec2b3
Add QDQ scale propagation pass (#713)
javier-intel Jul 3, 2025
3238a90
Added to remove MAC CI Warnings (#726)
sfatimar Jul 3, 2025
1695972
fix: Undo perf_runner changes (#727)
ankitm3k Jul 3, 2025
3106e3b
Merge branch 'master' into sync_msft_4_7_25
ankitm3k Jul 4, 2025
aa1730c
Merge pull request #730 from intel/sync_msft_4_7_25
ankitm3k Jul 4, 2025
efd14d9
Merge branch 'master' into sync_msft_7_7_25
ankitm3k Jul 7, 2025
66eceb9
Merge pull request #731 from intel/sync_msft_7_7_25
ankitm3k Jul 7, 2025
c9a5348
Merge branch 'master' into sync_msft_8_7_25
ankitm3k Jul 8, 2025
8264e36
Merge pull request #733 from intel/sync_msft_8_7_25
jatinwadhwa921 Jul 8, 2025
54151b1
Enable dynamic path for NPU when enable_causallm is true (#732)
RyanMetcalfeInt8 Jul 8, 2025
b4b9492
Merge branch 'master' into sync_msft_9_7_25
ankitm3k Jul 9, 2025
f89f64e
Merge pull request #734 from intel/sync_msft_9_7_25
ankitm3k Jul 9, 2025
8d36ad2
Allow zero-element tensors to get set (#737)
RyanMetcalfeInt8 Jul 10, 2025
89ccd81
Cluster Change to avoid Dangling DQLinear (#739)
sfatimar Jul 11, 2025
05126ff
Fix the model copies and redefinitions for CPU fallback (#728)
preetha-intel Jul 16, 2025
776bedf
Revert "Cluster Change to avoid Dangling DQLinear (#739)" (#743)
sfatimar Jul 16, 2025
bc3dc45
Sync ORT main 16 07 25 (#744)
ankitm3k Jul 16, 2025
bda52f6
Merge branch 'master' into sync_msft_17_7_25
ankitm3k Jul 17, 2025
87a7ac0
Revert "Sync ORT main 16 07 25 (#744)" (#745)
ankitm3k Jul 17, 2025
acb29b6
Merge pull request #746 from intel/sync_msft_17_7_25
ankitm3k Jul 17, 2025
ea8cf21
Added support for 2025.2 and enabled SimplifiedLayerNormalization op …
n1harika Jul 17, 2025
8642e8b
Merge branch 'master' into sync_ort_main_19_7_25
ankitm3k Jul 19, 2025
a616aba
Merge pull request #749 from intel/sync_ort_main_19_7_25
ankitm3k Jul 19, 2025
217f285
[OVEP] Fix coverity issues (#753)
jatinwadhwa921 Jul 21, 2025
138c6e0
[OVEP] feat: Integrate new ABI with Legacy OVEP Plugin (#747)
ankitm3k Jul 21, 2025
dfdda93
Merge branch 'master' into sync_msft_22_7_25
ankitm3k Jul 21, 2025
a90ebe5
Merge pull request #756 from intel/sync_msft_22_7_25
sfatimar Jul 21, 2025
01c762b
Merge branch 'master' into sync_msft_23_7_25
jatinwadhwa921 Jul 23, 2025
e1b2c28
Merge pull request #757 from intel/sync_msft_23_7_25
ankitm3k Jul 23, 2025
3faf7d9
ov_factory: Use 'GPU_DEVICE_ID' property to match with ORT device_id …
RyanMetcalfeInt8 Jul 23, 2025
99e516b
Merge branch 'master' into sync_msft_24_7_25
ankitm3k Jul 24, 2025
9c7a151
Merge pull request #760 from intel/sync_msft_24_7_25
ankitm3k Jul 24, 2025
2306b4a
[OVEP] Fix for upsample optype (#761)
jatinwadhwa921 Jul 25, 2025
1833f04
Merge branch 'master' into synccc_msft_29_7_25
ankitm3k Jul 29, 2025
420ec3a
Merge pull request #762 from intel/synccc_msft_29_7_25
ankitm3k Jul 29, 2025
5a583f9
Merge branch 'master' into sync_msft_31072025
Jaswanth51 Jul 31, 2025
ba8e3e7
Merge pull request #764 from intel/sync_msft_31072025
Jaswanth51 Jul 31, 2025
f4da9f1
[OVEP] Remove checks from load_config (#765)
jatinwadhwa921 Aug 1, 2025
ed9e425
Add self-detecting on-the-fly bfloat16->float16 conversion pass (#741)
mklimenk Aug 1, 2025
47a231a
[OVEP] Mild weight sharing- quantization paramters are kept as initia…
n1harika Aug 1, 2025
c533007
Merge pull request #766 from intel/niharika/mild_weight_sharing
n1harika Aug 5, 2025
ddc64b9
Merge branch 'master' into sync_msft_05082025
Jaswanth51 Aug 5, 2025
71f8877
Merge pull request #769 from intel/sync_msft_05082025
ankitm3k Aug 5, 2025
1170738
Merge branch 'master' into sync_msft_07082025
Jaswanth51 Aug 7, 2025
055300f
Merge pull request #770 from intel/sync_msft_07082025
ankitm3k Aug 7, 2025
7f7091e
Merge branch 'master' into sync_msft_08082025
Jaswanth51 Aug 8, 2025
c0c1ed7
Merge pull request #772 from intel/sync_msft_08082025
ankitm3k Aug 8, 2025
e4f8acb
Cluster Change to avoid Dangling DQLinear
TejalKhade28 Jul 11, 2025
aa31709
Error in subgraph
TejalKhade28 Jul 11, 2025
e77892e
Merge pull request #774 from intel/sahar/psu_lora
n1harika Aug 11, 2025
7ce9c96
Merge branch 'master' into sync_msft_12082025
Jaswanth51 Aug 12, 2025
07bf616
Merge pull request #775 from intel/sync_msft_12082025
Jaswanth51 Aug 12, 2025
725744a
Fix to set precision from config (#778)
preetha-intel Aug 13, 2025
609dfbf
Fix the load_config not work when set INFERENCE_PRECISION_HINT (#777)
sgbihu Aug 13, 2025
a780d5b
Fix failing case where input onnx model is used with shared context e…
javier-intel Aug 13, 2025
a6359ee
[OVEP] Support for providing layout to input/output to OpenVINO (#767)
jatinwadhwa921 Aug 14, 2025
f05d669
Merge branch 'master' into sync_msft_18082025
Jaswanth51 Aug 18, 2025
78e46e2
Merge pull request #780 from intel/sync_msft_18082025
ankitm3k Aug 18, 2025
6dd04a5
Merge branch 'master' into sync_msft_20082025
Jaswanth51 Aug 20, 2025
aea572d
Merge pull request #781 from intel/sync_msft_20082025
ankitm3k Aug 20, 2025
e634654
OVInferRequest::SetTensor: Set tensor upon cached_binding shape misma…
RyanMetcalfeInt8 Aug 21, 2025
0bad3d7
Updated load_config mapping to make it a passthrough to OV properties…
ankitm3k Aug 22, 2025
cb59e2d
Merge branch 'master' into sync_msft_25082025
Jaswanth51 Aug 25, 2025
e812aea
Merge pull request #789 from intel/sync_msft_25082025
ankitm3k Aug 25, 2025
8ecdbd0
Fix model copying for QDQ stripping (#784)
mklimenk Aug 25, 2025
e974fbe
Sahar/psu lora fix 2 (#788)
sfatimar Aug 25, 2025
ed6d8e0
Commit PSU Lora fix (#791)
sfatimar Aug 25, 2025
6aa8420
Fix to resolve EPCtx filename confusion with wrapped OVIRs (#793)
gblong1 Aug 25, 2025
866a24c
Allow mmapping native binaries in ov 2025.3 (#794)
ericcraw Aug 26, 2025
7eafccb
fix: lint fixes (#795)
ankitm3k Aug 26, 2025
e019aa1
Update operator support status for OpenVINO 2025.2 (#792)
preetha-intel Aug 26, 2025
167f2ad
[OVEP] Fix cov issues (#796)
jatinwadhwa921 Aug 28, 2025
676a4d2
Merge branch 'master' into sync_msft_28082025
Jaswanth51 Aug 28, 2025
b9a1885
Merge pull request #797 from intel/sync_msft_28082025
Jaswanth51 Aug 28, 2025
b7244f1
remove onnxruntime/test/providers/openvino/openvino_plugin.cc (#798)
RyanMetcalfeInt8 Aug 28, 2025
be346bb
OVEP-CI updating version (#799)
jatinwadhwa921 Sep 1, 2025
2f1ad9d
Sync with Microsoft ONNX Runtime - 01/09/2025 (#801)
Jaswanth51 Sep 1, 2025
cc8b267
Revert "Sync with Microsoft ONNX Runtime - 01/09/2025 (#801)"
Jaswanth51 Sep 2, 2025
161e645
Merge pull request #803 from intel/revert-801-sync_msft_01092025
Jaswanth51 Sep 2, 2025
c3276de
Re-enable setting default precision for OV devices (#802)
preetha-intel Sep 2, 2025
edc51ea
bf16 tensor handling related fix (#805)
susbhere Sep 3, 2025
fba645c
Merge branch 'master' into sync_msft_10_9_25
jatinwadhwa921 Sep 10, 2025
3215fef
Merge pull request #810 from intel/sync_msft_10_9_25
jatinwadhwa921 Sep 11, 2025
a5bd8ee
[OVEP] Fix to increase provider value upto 2048 char (#807)
jatinwadhwa921 Sep 11, 2025
02cf7e3
Make cache_dir and num_stream options session-local (#809)
mklimenk Sep 12, 2025
f3d7b4f
Merge branch 'master' into sync_msft_15092025
Jaswanth51 Sep 15, 2025
c098113
Merge pull request #811 from intel/sync_msft_15092025
ankitm3k Sep 15, 2025
42b1fbb
Merge branch 'master' into sync_msft_17092025
Jaswanth51 Sep 17, 2025
f7a5656
Merge pull request #814 from intel/sync_msft_17092025
ankitm3k Sep 17, 2025
58e83ef
Fix performance degradation in Ubuntu (#815)
jwludzik Sep 23, 2025
89db8a4
Merge branch 'master' into sync_msft_26092025
Jaswanth51 Sep 26, 2025
9d56532
Merge pull request #818 from intel/sync_msft_26092025
Jaswanth51 Sep 26, 2025
ce3a033
Merge branch 'master' into sync_msft_01102025
Jaswanth51 Oct 1, 2025
2d82713
Merge pull request #820 from intel/sync_msft_01102025
ankitm3k Oct 1, 2025
f8b0904
Don't embed external initializers into the proto to avoid 2GB limit (…
intbf Oct 6, 2025
d102554
Fix Regression in Model PSS and PSR, add check for zero-size initiali…
intbf Oct 9, 2025
9a5e182
Merge branch 'master' into sync_msft_10102025
Jaswanth51 Oct 10, 2025
2652479
Merge pull request #826 from intel/sync_msft_10102025
ankitm3k Oct 10, 2025
b685871
When dynamic shapes are used the proto might be overriden and offsets…
intbf Oct 10, 2025
65bbecc
trigger stateful path for Phisilica model
Kotomi-Du Oct 2, 2025
1e132f3
unify the code
Kotomi-Du Oct 11, 2025
59f22e1
[OVEP] fixed NPU exception message when CPU fallback is disabled (#832)
RajeevSekar Oct 14, 2025
5c40da5
CVS-174886: Make onnxruntime tests pass on OpenVINO (#790)
sgbihu Oct 14, 2025
914c07a
[OVEP] Enable Session Option to Stop Context Sharing (#822)
n1harika Oct 15, 2025
37b99c1
Merge branch 'master' into sync_msft_16102025
Jaswanth51 Oct 16, 2025
f7483e6
Merge pull request #833 from intel/sync_msft_16102025
ankitm3k Oct 16, 2025
19ebc1f
CVS-174008: Enable ETW Tracing for OVEP (#827)
ankitm3k Oct 16, 2025
25c6976
address PR review
Kotomi-Du Oct 17, 2025
397c61b
CVS-174585: Memory map shared weights when possible (#829)
ericcraw Oct 22, 2025
8e9ecb7
Merge branch 'master' into sync_msft_27102025
Jaswanth51 Oct 27, 2025
c7204c5
Merge pull request #835 from intel/sync_msft_27102025
ankitm3k Oct 27, 2025
6d41065
Run lintrunner and fix formatting issues (#836)
Jaswanth51 Oct 27, 2025
eff6cac
CVS-175734- [OVEP GPU] add GQA in support list for GPU backend (#830)
Kotomi-Du Oct 27, 2025
b1f7750
CVS-175737-[OVEP] Expose kvcache_rewind python api (#831)
Kotomi-Du Oct 28, 2025
513e198
update the keyword for matching key_value_input_names
Kotomi-Du Oct 28, 2025
20de366
CVS-175447-[OVEP] Add a check for type mismatches in QDQ stripping (#…
mdvoretc-intel Oct 29, 2025
d7ee534
optimize the code
Kotomi-Du Oct 30, 2025
3c1c4c3
revert original code which is functional
Kotomi-Du Oct 30, 2025
7c1720d
remove useless change
Kotomi-Du Oct 30, 2025
81772e9
Merge branch 'master' into sync_msft_03112025
Jaswanth51 Nov 3, 2025
323cfeb
Merge pull request #843 from intel/sync_msft_03112025
ankitm3k Nov 3, 2025
2041402
Merge branch 'ovep-develop' into make_stateful_phisilica
Kotomi-Du Nov 3, 2025
b9a73f3
Merge pull request #821 from Kotomi-Du/make_stateful_phisilica
Kotomi-Du Nov 3, 2025
7aa5363
[OVEP] support to run layout feature using python bindings (#846)
jatinwadhwa921 Nov 7, 2025
fa68db1
CVS-176081: Add support for nested maps to load_config parsing (#844)
RyanMetcalfeInt8 Nov 7, 2025
70acefe
[CVS-172796] fix bfloat16 conversion when single cast node to bfloat1…
bopeng1234 Nov 11, 2025
5743197
ov_stateful_patch_utils: Remove NPUW WA for avoiding SinCos when cont…
RyanMetcalfeInt8 Nov 13, 2025
10af800
CVS-175880 Implement single bin (#847)
ericcraw Nov 13, 2025
52c88df
Merge branch 'master' into sync_msft_14112025
Jaswanth51 Nov 14, 2025
0f8a754
Merge pull request #848 from intel/sync_msft_14112025
ankitm3k Nov 14, 2025
51493cd
Run lintrunner and fix formatting issues (#849)
Jaswanth51 Nov 14, 2025
d0bac3e
CVS-175736 - [OVEP] Optimize Stateful Path: use output-to-input strat…
Kotomi-Du Nov 15, 2025
75c11ae
CVS-167480 : Report import failure error code (#715)
javier-intel Nov 17, 2025
d951954
CVS-175504: Additional single bin simplifications + fixes for bi-dire…
ericcraw Nov 17, 2025
0d68ee5
CVS-176574 : Fix memory leaks for protobuf & DataOps (#852)
ankitm3k Nov 18, 2025
dbd1ce0
CVS-175504 Fix mixing weight shared and non-shared models (#854)
ericcraw Nov 19, 2025
fa7ab09
ovep stateful: Enable explicit slice of prefill logits when NPUW_SLIC…
RyanMetcalfeInt8 Nov 19, 2025
24c833c
Updating OVEP to support 2025.4.0 (#853)
jatinwadhwa921 Nov 19, 2025
4b1976a
Merge branch 'master' into sync_msft_19112025
Jaswanth51 Nov 19, 2025
a69cbf7
CVS-175119-[OVEP] Fixed possibility of array index out of bounds in s…
RajeevSekar Nov 19, 2025
cb8c270
Merge branch 'ovep-develop' into sync_msft_19112025
preetha-intel Nov 19, 2025
ade6a2e
Merge pull request #856 from intel/sync_msft_19112025
ankitm3k Nov 19, 2025
2f7212c
skipped failing testcase (MathOpTest.Clip_Default_int64) (#860)
RajeevSekar Nov 20, 2025
5a06f68
reset ort.eprp file changes (#862)
ankitm3k Nov 25, 2025
6274e3c
Merge branch 'master' into sync_msft_25112025
Jaswanth51 Nov 25, 2025
bb738ba
Merge pull request #863 from intel/sync_msft_25112025
Jaswanth51 Nov 25, 2025
39d6db5
Sync with Microsoft ONNX Runtime - 03/12/2025 (#867)
Jaswanth51 Dec 3, 2025
8291389
Revert "Sync with Microsoft ONNX Runtime - 03/12/2025 (#867)"
Jaswanth51 Dec 3, 2025
fa8f464
Merge pull request #868 from intel/revert_sync_03122025
Jaswanth51 Dec 3, 2025
1279a44
disable QDQ scale-strip for 2025.0
nazanin-beheshti Dec 9, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 45 additions & 0 deletions .github/workflows/linux_openvino_ci_intel.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,45 @@
name: Linux OpenVINO CI

on:
push:
branches: [ main, 'rel-*' ]
pull_request:
branches: ['**' ]
workflow_dispatch:

concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true

permissions:
contents: read
packages: write # Needed if the reusable workflow pushes images
attestations: write # Optional: for artifact attestations if enabled
id-token: write # Optional: may be needed for OIDC authentication (e.g., ACR)

jobs:
build_test_openvino:
name: Build and Test OpenVINO EP (AlamLinux8, Py3.12)
# Use the reusable workflow as the other Linux CI pipelines
uses: ./.github/workflows/reusable_linux_build_intel.yml
with:
pool_name: "onnxruntime-github-Ubuntu2204-AMD-CPU"
build_config: Release
# Architecture: OpenVino only supports Intel X64
architecture: x64
dockerfile_path: tools/ci_build/github/linux/docker/inference/x86_64/python/openvino/Dockerfile
docker_image_repo: onnxruntimeopenvino

execution_providers: 'openvino'

extra_build_flags: '--use_openvino CPU --enable_generic_interface --build_shared_lib'

# Python Path Prefix: Set the correct Python 3.12 path inside the manylinux container
python_path_prefix: 'PATH=/opt/python/cp312-cp312/bin:$PATH'

run_tests: true
upload_build_output: false

# Secrets: Pass the necessary GitHub token
secrets:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
183 changes: 183 additions & 0 deletions .github/workflows/reusable_linux_build_intel.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,183 @@
name: Reusable Linux CPU/GPU Build and Test

on:
workflow_call:
inputs:
pool_name:
description: 'The specific 1ES pool name (e.g., onnxruntime-github-Ubuntu2204-AMD-CPU)'
required: true
type: string
build_config:
description: 'Build configuration (Debug or Release)'
required: true
type: string
architecture:
description: 'Target architecture (x64 or arm64)'
required: true
type: string
dockerfile_path:
description: 'Path to the Dockerfile relative to the workspace root'
required: true
type: string
docker_image_repo:
description: 'Name for the Docker image repository'
required: true
type: string
docker_build_args:
description: 'Arguments to pass to the docker image build command'
required: false
type: string
default: ''
execution_providers:
description: 'Space-separated list of execution providers to enable (passed to build.py)'
required: false
type: string
default: ''
extra_build_flags:
description: 'Additional flags for the build.py script (appended after EP flags)'
required: false
type: string
default: ''
python_path_prefix:
description: 'Optional prefix to add to the PATH for python command (e.g., PATH=/opt/python/cp310-cp310/bin:$PATH)'
required: false
type: string
default: ''
python_version:
description: 'Python version to set up on the runner host'
required: false
type: string
default: '3.x'
run_tests:
description: 'Whether to execute the test suite after building'
required: false
type: boolean
default: true
upload_build_output:
description: 'Whether to upload the build output directory as an artifact (used when tests are skipped)'
required: false
type: boolean
default: false
secrets:
GH_TOKEN:
description: 'GitHub token for accessing actions/packages'
required: true

jobs:
build_test_pipeline:
runs-on: [self-hosted, Linux, X64]
permissions:
contents: read
packages: write
attestations: write
id-token: write
steps:
- name: Checkout code
uses: actions/checkout@v5

- name: Set up Python ${{ inputs.python_version }}
uses: actions/setup-python@v5
with:
python-version: ${{ inputs.python_version }}

- name: Build Docker Image (${{ inputs.architecture }} / ${{ inputs.build_config }})
uses: microsoft/onnxruntime-github-actions/[email protected]
id: build_docker_image_step
with:
dockerfile: ${{ github.workspace }}/${{ inputs.dockerfile_path }}
image-name: ghcr.io/microsoft/onnxruntime/${{ inputs.docker_image_repo }}
build-args: ${{ inputs.docker_build_args }}
push: true
azure-container-registry-name: onnxruntimebuildcache
env:
GITHUB_TOKEN: ${{ secrets.GH_TOKEN }}

- name: Export GitHub Actions cache environment variables
uses: actions/github-script@v7
with:
script: |
core.exportVariable('ACTIONS_CACHE_URL', process.env.ACTIONS_CACHE_URL || '');
core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || '');
# ------------- Update Step (CMake Generation) -------------
- name: Generate Build Files (CMake) (${{ inputs.architecture }} / ${{ inputs.build_config }})
id: update_step
uses: microsoft/onnxruntime-github-actions/[email protected]
with:
docker_image: ${{ steps.build_docker_image_step.outputs.full-image-name }}
build_config: ${{ inputs.build_config }}
mode: 'update'
execution_providers: ${{ inputs.execution_providers }} # Pass down EP list
extra_build_flags: ${{ inputs.extra_build_flags }}
python_path_prefix: ${{ inputs.python_path_prefix }}

# ------------- Build Step (Compilation) -------------
- name: Build ONNX Runtime (${{ inputs.architecture }} / ${{ inputs.build_config }})
id: build_step
uses: microsoft/onnxruntime-github-actions/[email protected]
with:
docker_image: ${{ steps.build_docker_image_step.outputs.full-image-name }}
build_config: ${{ inputs.build_config }}
mode: 'build'
execution_providers: ${{ inputs.execution_providers }} # Pass down EP list
extra_build_flags: ${{ inputs.extra_build_flags }}
python_path_prefix: ${{ inputs.python_path_prefix }}

# ------------- Test Step -------------
- name: Test ONNX Runtime (${{ inputs.architecture }} / ${{ inputs.build_config }})
id: test_step
if: inputs.run_tests == true
uses: microsoft/onnxruntime-github-actions/[email protected]
with:
docker_image: ${{ steps.build_docker_image_step.outputs.full-image-name }}
build_config: ${{ inputs.build_config }}
mode: 'test'
execution_providers: ${{ inputs.execution_providers }} # Pass down EP list
extra_build_flags: ${{ inputs.extra_build_flags }}
python_path_prefix: ${{ inputs.python_path_prefix }}

# ------------- Prepare Artifact Step -------------
- name: Prepare Build Output for Upload
if: inputs.upload_build_output == true
shell: bash
run: |
#!/bin/bash
set -e -x
BUILD_DIR="${{ runner.temp }}/${{ inputs.build_config }}"
if [ ! -d "${BUILD_DIR}" ]; then
echo "Error: Build directory ${BUILD_DIR} not found. Cannot prepare artifact."
exit 1
fi
echo "--- Cleaning build directory: ${BUILD_DIR} ---"
rm -rf "${BUILD_DIR}/onnxruntime" || true
rm -rf "${BUILD_DIR}/pybind11" || true
rm -rf "${BUILD_DIR}/vcpkg_installed" || true
rm -f "${BUILD_DIR}/models" || true
DEPS_DIR="${BUILD_DIR}/_deps"
if [ -d "${DEPS_DIR}" ]; then
echo "Cleaning ${DEPS_DIR}, keeping onnx-src..."
find "${DEPS_DIR}" -mindepth 1 ! -regex "^${DEPS_DIR}/onnx-src\(/.*\)?$" -delete
else
echo "${DEPS_DIR} does not exist, skipping deps cleanup."
fi
echo "--- Saving executable permissions ---"
cd "${BUILD_DIR}"
find . -executable -type f -printf '%p\n' > perms.txt
echo "--- Cleanup and permission saving complete for ${BUILD_DIR} ---"

# ------------- Upload Build Output Step -------------
- name: Upload Build Output Artifact
if: inputs.upload_build_output == true
uses: actions/upload-artifact@v4
with:
name: build-output-${{ inputs.architecture }}-${{ inputs.build_config }}
path: ${{ runner.temp }}/${{ inputs.build_config }}
if-no-files-found: error

# ------------- Upload Log on Build Failure Step -------------
- name: Upload VCPKG Manifest Install Log on Update or Build Failure
if: steps.update_step.outcome == 'failure' || steps.build_step.outcome == 'failure'
uses: actions/upload-artifact@v4
with:
name: vcpkg-manifest-install-log-${{ inputs.architecture }}-${{ inputs.build_config }}
path: ${{ runner.temp }}/${{ inputs.build_config }}/${{ inputs.build_config }}/vcpkg-manifest-install.log
if-no-files-found: ignore
10 changes: 10 additions & 0 deletions cmake/onnxruntime_providers_openvino.cmake
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,11 @@
source_group(TREE ${ONNXRUNTIME_ROOT}/core FILES ${onnxruntime_providers_openvino_cc_srcs})
onnxruntime_add_shared_library_module(onnxruntime_providers_openvino ${onnxruntime_providers_openvino_cc_srcs} "${ONNXRUNTIME_ROOT}/core/dll/onnxruntime.rc")

# Propagate leak check define if enabled at top level
if(onnxruntime_ENABLE_MEMLEAK_CHECKER)
target_compile_definitions(onnxruntime_providers_openvino PRIVATE ONNXRUNTIME_ENABLE_MEMLEAK_CHECK)
endif()

onnxruntime_add_include_to_target(onnxruntime_providers_openvino onnxruntime_common onnx nlohmann_json::nlohmann_json)
install(FILES ${PROJECT_SOURCE_DIR}/../include/onnxruntime/core/providers/openvino/openvino_provider_factory.h
DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/onnxruntime/)
Expand All @@ -51,6 +56,11 @@
target_include_directories(onnxruntime_providers_openvino SYSTEM PUBLIC ${ONNXRUNTIME_ROOT} ${CMAKE_CURRENT_BINARY_DIR} ${OpenVINO_INCLUDE_DIR} ${OPENVINO_INCLUDE_DIR_LIST} ${PYTHON_INCLUDE_DIRS} $ENV{OPENCL_INCS} $ENV{OPENCL_INCS}/../../cl_headers/)
target_link_libraries(onnxruntime_providers_openvino ${ONNXRUNTIME_PROVIDERS_SHARED} Boost::mp11 ${OPENVINO_LIB_LIST} ${ABSEIL_LIBS} Eigen3::Eigen onnx_proto)

# ETW TraceLogging depends on Advapi32 on Windows
if(WIN32)
target_link_libraries(onnxruntime_providers_openvino advapi32)
endif()

target_compile_definitions(onnxruntime_providers_openvino PRIVATE FILE_NAME=\"onnxruntime_providers_openvino.dll\")

if(MSVC)
Expand Down
4 changes: 4 additions & 0 deletions onnxruntime/core/dll/dllmain.cc
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,10 @@ BOOL APIENTRY DllMain(HMODULE /*hModule*/,
if (lpvReserved != nullptr) {
g_is_shutting_down = true;
// do not do cleanup if process termination scenario
#if defined(ONNXRUNTIME_ENABLE_MEMLEAK_CHECK)
// In leak-check builds we still want protobuf shutdown to avoid flagged leaks.
::google::protobuf::ShutdownProtobufLibrary();
#endif
} else {
// Cleanup protobuf library.
// NOTE: it might be too early to do so, as all function local statics and global objects are not destroyed yet.
Expand Down
Loading