Skip to content
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

Fix tf fe input shape #40

Merged
merged 905 commits into from
Oct 25, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
905 commits
Select commit Hold shift + click to select a range
c928fde
[MO] Remove Apache MxNet models support in openvino-dev (#26800)
rkazants Sep 30, 2024
9b0d209
[DOCS] post-release polishing pass 4 mstr (#26866)
kblaszczak-intel Sep 30, 2024
2507d89
Handle dynamic rank in TSUnsqueezeBackward transformation (#26786)
itikhono Sep 30, 2024
d2a9873
[GHA][PE FE][TF FE] Create separate GHA job for PyTorch layer tests a…
rkazants Oct 1, 2024
9284684
[Snippets][CPU] Added dynamic MatMul INT8/BF16 support (#26493)
a-sidorova Oct 1, 2024
ad448dd
[NPUW] Add initial unpack and partitioning unit tests on NPUW (#25780)
smirnov-alexey Oct 1, 2024
18c852e
Revert "[NPUW] Add initial unpack and partitioning unit tests on NPUW…
ababushk Oct 2, 2024
98adad1
[coverity, core] Fix unchecked return value in bound evaluate (#26768)
praasz Oct 2, 2024
32aaa2f
[OV JS] Add TS definition for AnyMap (#26711)
almilosz Oct 2, 2024
205c11e
[NPU] Add documentation for batching on NPU plugin (#26865)
pereanub Oct 2, 2024
0b21860
NPUW: Fix nullptr reference parameter in rearrange_to_proto (#26869)
AsyaPronina Oct 2, 2024
cddcfe8
single-image-test: added accuracy workaround for computing CPU refere…
beleiuandrei Oct 2, 2024
17ecf03
[GPU] Support large N FC optimization for dynamic quantization case (…
andrew-k-park Oct 3, 2024
4254c13
NPUW: Bring back unpack and partitioning unit tests for NPUW (#26885)
AsyaPronina Oct 3, 2024
0ae4484
[PT FE][GHA] Run PT FE layer tests on Ubuntu 24.04 with Python 3.12 a…
rkazants Oct 3, 2024
1b892bf
[GPU] Fix double jit constants (#26893)
p-durandin Oct 3, 2024
2fc0fae
[TF FE]: Support complex tensors for ExpandDims operation (#26892)
hub-bla Oct 3, 2024
5c1e1fb
[GPU] Extract debug code from network::execute() (#26888)
Oct 3, 2024
108bb73
[GPU] Fix unit tests ph4 (#26879)
p-durandin Oct 3, 2024
0ae3683
[GPU] Adjust usm_host memory usage for InferRequest tensors (#26896)
sshlyapn Oct 3, 2024
890f2e1
[GPU] Fix empty oneDnn users (#26900)
p-durandin Oct 3, 2024
500284d
[TF FE][Keras] Use latest Keras for TF FE validation and adopt tests …
rkazants Oct 7, 2024
0a348d8
[core] Convert reference use intrinsic implementation for ChromeOS (…
praasz Oct 7, 2024
cf870cd
Fix ov RTTI (#26895)
itikhono Oct 7, 2024
0aa76e7
[PT FE] Fix torchaudio dependency for MacOS x86 (#26913)
rkazants Oct 7, 2024
fc97aaa
Docs Add Category to Coveo search engine (#26932)
akopytko Oct 7, 2024
2c6d1bb
[DOCS] Fixing references to Node.js methods (#26933)
sgolebiewski-intel Oct 7, 2024
2167b03
[GHA] Don't update latest available artifacts link when copy failed (…
akladiev Oct 7, 2024
de94a33
[GPU] network code cleanup (#26908)
Oct 7, 2024
8151e00
[DOCS] technical adjustments for the build mstr (#26883)
kblaszczak-intel Oct 7, 2024
339a956
[NPUW] Better utilize threads on compilation (#26864)
smirnov-alexey Oct 7, 2024
e2c3982
Eliminate nop Convert at the beginning of the MOC pipeline (#26872)
itikhono Oct 7, 2024
9027e1d
[PT FE] Fix Bitwise translators with 3 inputs (#26930)
rkazants Oct 7, 2024
46a6ccd
List decompositions for torch.export (#26878)
mvafin Oct 7, 2024
3c7e7d9
[DOCS] release notes one more adjustment (#26876)
kblaszczak-intel Oct 8, 2024
737caf5
[PT FE] Support prim::fork and aten::wait (#26839)
mvafin Oct 8, 2024
2b129e2
[PT FE] Remove explicit optimum deps from validation (#26948)
rkazants Oct 8, 2024
4b43150
Update h5py requirement from <3.12.0,>=3.1.0 to >=3.1.0,<3.13.0 in /s…
dependabot[bot] Oct 8, 2024
0882ff6
Use get_partial_shape to get dynamic shape (#26907)
ArtemySkrebkov Oct 8, 2024
4d3a534
[DOCS] Updating Interactive Tutorials (#26947)
sgolebiewski-intel Oct 8, 2024
4a30cb8
[NPU] Adding support for the set_tensors method (#26823)
pereanub Oct 8, 2024
0ebff04
[NPU] Use different graph init (#26903)
pereanub Oct 8, 2024
9c65ba2
[Snippets] Tokenization helper cleanup and tokenization tests reenabl…
v-Golubev Oct 8, 2024
2efd2b1
[ONNX] Added support for dynamic input shapes in com.microsoft.MatMul…
gkrivor Oct 8, 2024
ed53a64
[GHA] use pigz with tar (#26954)
mryzhov Oct 8, 2024
4672d2e
[ov_integration] Remove incompatible test (#26917)
sbutnari Oct 9, 2024
73e9c6c
[GHA] Automatically choose merge queue base branch in restore artifac…
akladiev Oct 9, 2024
8517c36
[Op]: Added SearchSorted op def. (#26904)
pkowalc1 Oct 9, 2024
5a92485
NPUW: Fix DCOFF patterns and handling for NNCF 2.12's GPTQs (#26955)
dmatveev Oct 9, 2024
37957c9
[GPU] Fix unit tests ph5 (#26911)
p-durandin Oct 9, 2024
168c1e5
QF Sitemap Url wrapper (#26971)
akopytko Oct 9, 2024
46736bc
[GHA] Pin upload-artifact version in provider (#26970)
akladiev Oct 9, 2024
1c01983
[GPU] Extend deconv parameters to match size for onednn (#26793)
steve-y Oct 9, 2024
9d98a8d
[NPUW] Support submodels caching and stabilize inputs/outputs order o…
smirnov-alexey Oct 9, 2024
cbf42f3
NPUW: Spatial execution (#26880)
dmatveev Oct 9, 2024
3236bec
[NPUW] Recent coverity fix (#26905)
smirnov-alexey Oct 9, 2024
ebeee18
[GPU] Conv should not extend strides and dilations for 3d output (#26…
kelvinchoi-intel Oct 10, 2024
b813ec6
[GPU] Fix fc 4d for onednn (#26479)
steve-y Oct 10, 2024
f90f7bb
[NPUW] Update nullptr fix for parameters (#26926)
AsyaPronina Oct 10, 2024
d499a16
[GPU] Fix setting dependency input when unfusing subgraph (#26959)
davidsnam-intel Oct 10, 2024
cab5b2c
[GPU] Fix accuracy issue at gemm_tiled_opt kernel with dynamic paddin…
kelvinchoi-intel Oct 10, 2024
7eb14b7
[GPU] Use ifm size of fc for dynamic quantize (#26850)
jade-cho Oct 10, 2024
82c4566
[CPU] SliceScatter-15 CPU implementation (#26285)
mmikolajcz Oct 10, 2024
faa3ab2
[GHA] Exclude onnx runtime files from package (#26973)
mryzhov Oct 10, 2024
3f70084
[CPU] [Snippets] [ARM] Support precision f16 for Snippets on ARM and …
xuchen-intel Oct 10, 2024
69bd556
[core] Constant can be created as from shared memory (#26901)
praasz Oct 10, 2024
aba9c35
Skip test_tf_Bucketize for boundaries_size is 0 on GPU (#26987)
davidsnam-intel Oct 10, 2024
7d5b7cf
[GPU] fix fused_select_reorder (#26965)
zaixing-wang Oct 10, 2024
f1ef55d
[FRONTEND] Remove unnecessary Reshapes in PyTorch Conv1D conversion (…
CuriousPanCake Oct 10, 2024
1f7946e
[GHA] Fix sanitizers tests trigger in forks (#26990)
akladiev Oct 10, 2024
be0135e
Updated protobuf to v21.12 to be aligned with ONNX Runtime (#26984)
ilya-lavrenov Oct 10, 2024
cbc29ee
[NPUW] Update weights bank and closures to operate on top of DQ trans…
smirnov-alexey Oct 10, 2024
fee50b0
[GPU] Improve MVN BFYX OPT kernel sum reductions (#26346)
dnkurek Oct 10, 2024
0361714
NPUW: Various fixes for FUNCALL_FOR_ALL (#26937)
dmatveev Oct 10, 2024
79e229b
Allow to Build OpenVINO with Python3.13 (#27000)
akuporos Oct 11, 2024
b212815
[ref]: Added SearchSorted ref impl (#26958)
pkowalc1 Oct 11, 2024
5f9a55a
Turn on support of std::filesystem::path for all build targets (#26953)
barnasm1 Oct 11, 2024
285c352
[CPU][OMP] Fix for functional tests (#26801)
nshchego Oct 11, 2024
8a02b4c
[GPU] switch onednn primitive to use other primitive_impl constructor…
DrewBearly Oct 11, 2024
6af61f4
Exclude JAX FE from all distributions except wheel (#26610)
ilya-lavrenov Oct 11, 2024
d9806d8
[GHA] Increase timeout for Pytorch layer tests (#26994)
dorloff Oct 11, 2024
ecec879
[GPU] Fix OOB in lrn (#26979)
p-durandin Oct 11, 2024
3976549
[CI] [GHA] Introduce C++ unittests on Debian ARM (#26656)
akashchi Oct 11, 2024
b354be8
[GSOC][CPU][ARM] Add fp16 support for SDPA (#25918)
mory91 Oct 11, 2024
ec466ac
[ONNX] Added default_op_checks function (#26969)
gkrivor Oct 11, 2024
50f78fd
[TESTS] Remove restart condition as it happens in nested exception (#…
mvafin Oct 11, 2024
ebfefab
[OV JS] Fix preprocessing layout in hello_classification demo (#26594)
vishniakov-nikolai Oct 11, 2024
f7081a7
[PT FE] Disable support for cuda GPTQ type, since it was never suppor…
mvafin Oct 11, 2024
e2b09ea
[PT FE] Extract signature for FX scenario (#27014)
mvafin Oct 11, 2024
ea14d29
[PT FE] Support aten::unsafe_chunk op (#26931)
mvafin Oct 11, 2024
591c7ac
temporarily disable sample proto unit-test (#27004)
pavel-esir Oct 11, 2024
fefe9bd
[core] fix bug in values_info::predicate (#26982)
usstq Oct 12, 2024
5897e55
[MO] Clean up requirements due to drop of Python 3.8 (#27009)
rkazants Oct 12, 2024
eb98c8e
[CPU] Enable mmap for model loading from cache. (#23315)
nshchego Oct 12, 2024
c714284
[TF FE][PT FE] Update labels with reqs files (#27020)
rkazants Oct 12, 2024
7250c1e
[CPU] Enabled FP16 Compressed FC on models with PagedAttention (#26279)
Oct 14, 2024
b7d1f1d
[SearchSortedDef]: Bugfixes in shape_infer. (#27013)
pkowalc1 Oct 14, 2024
0cfe282
[`intel-npu`] [`SUPPORT INTERNAL OPERATORS`] [`RMS`] Add support for …
MirceaDan99 Oct 14, 2024
52b4ea0
[CPU][ARM64] Add JIT emitter for Eltwise SoftSign operation (#26920)
nashez Oct 14, 2024
136e59c
[PT FE] Support conversion of TorchScript and ExportedProgram from di…
rkazants Oct 14, 2024
9c432a3
Fix gather kernel bug for handling 5 and 6 dimensions (#26894)
clee30 Oct 14, 2024
6581fee
[DOCS] OV GenAI Python API for master (#27028)
tadamczx Oct 14, 2024
f61db78
[DOCS] Add Ovem files to folder (#27029)
akopytko Oct 14, 2024
87e463e
NPUW: Fix - don't register an extra parameter to a group (#27032)
dmatveev Oct 14, 2024
7f85f15
Place wheels to a separate folder (#26952)
mryzhov Oct 14, 2024
e78f518
[GHA] Configurable event name for provider (#27035)
akladiev Oct 14, 2024
062762b
[NPUW] L0 allocation improvements (#27011)
smirnov-alexey Oct 14, 2024
b2782fa
[GHA] Fix wheels storage handling (#27039)
akladiev Oct 14, 2024
c44a32e
[GPU] Fix sd1.5_controlnet_lora bad image. (#26881)
hyunback Oct 14, 2024
421eaec
[GHA] Include files in plain subfolders to restore (#27046)
akladiev Oct 15, 2024
fe2f67b
Assert on minimal macOS deployment target (#26136)
ilya-lavrenov Oct 15, 2024
9486b7d
[CPU] attn supports f16 (#26487)
azhai219 Oct 15, 2024
dc7f4ae
[DOCS] Fixed tests for Ovms folder path (#27049)
akopytko Oct 15, 2024
06eb814
[CPU] Optimize MemoryInput/Output for empty shapes (#27015)
maxnick Oct 15, 2024
96032f3
[Core/Ref] Fix Proposal swap_xy selection (#26986)
t-jankowski Oct 15, 2024
03773f7
[CI] [GHA] Use the default `gcc` in Ubuntu 20 (#26993)
akashchi Oct 15, 2024
01ceeb8
[CPU]Fix heap buffer overflow in DenormalNullifyCheck (#27047)
zhangYiIntel Oct 15, 2024
2d00d75
[OVC][PT FE] Cover leftovers for torch.export.ExportedProgram support…
rkazants Oct 15, 2024
6beeb76
[DOCS] tiny NPU adjustment-mstr (#27033)
kblaszczak-intel Oct 15, 2024
d8d1149
Initial py3.8 removal (#26468)
akuporos Oct 15, 2024
6526155
[DOCS] Removed OMZ from the build (#27052)
tadamczx Oct 15, 2024
8effdd4
[OV JS][DOCS] Edits in JS API docs (#26875)
vishniakov-nikolai Oct 15, 2024
b2cd7aa
[CPU] Support degenerate matrices in MatMul (#26830)
maxnick Oct 15, 2024
296ab9a
[Docs] Update files for ovms benchmarks (#27058)
akopytko Oct 15, 2024
3ff0943
NPUW: Function memory management (#27043)
dmatveev Oct 15, 2024
341de8d
Use find_library to find clang on linux (#27040)
ArtemySkrebkov Oct 15, 2024
485e580
Fixed tests for NPUW (#27060)
AsyaPronina Oct 15, 2024
d52cf4a
Update numpy in tests reqs (#27061)
akuporos Oct 15, 2024
c6801aa
[NPUW] extend DQ & PMM processing and make reduceSum not to keep axis…
shaojun-yao Oct 15, 2024
4afbcbd
NPUW: Enable PMM for prefill by default (#27057)
dmatveev Oct 15, 2024
0663325
[NPUW] Polished NPUW tests fix and added NPUW tests paths to labeler …
AsyaPronina Oct 16, 2024
58073ca
Shape inference improvements for `SearchSorted-15` (#26980)
p-wysocki Oct 16, 2024
005152a
Enable mmap for reading model from cache (#26696)
olpipi Oct 16, 2024
1693821
[DOCS] nncf changes pass 3 recommend (#26873)
kblaszczak-intel Oct 16, 2024
8597d9a
[GHA] Install pigz on macOS (#27003)
mryzhov Oct 16, 2024
bf60502
[GPU] Fix SD3 int4 OOR or Perf drop issue in LNL (#27079)
hyunback Oct 16, 2024
80d6fdf
[ONNX] Added initial support of DequantizeLinear-21 (#26915)
gkrivor Oct 16, 2024
6856813
[CPU][ARM64] Add JIT emitter for Eltwise Sqrt operation (#27023)
nashez Oct 16, 2024
6b1081e
[GPU] Added empty LoRA adapters support (#26951)
Lyamin-Roman Oct 16, 2024
b5a0c60
[GPU] Support RoPE kernel for ChatGLM4 (#26799)
ahnyoung-paul Oct 16, 2024
15072ab
[GPU] limit skip of reorder if input is on constant path (#26509)
WeldonWangwang Oct 16, 2024
324a282
NPUW: Regularized REP pipeline (#27089)
dmatveev Oct 16, 2024
262f920
[GPU] Fix bug in GatherND reference GPU kernel (#27041)
JamesMBartlett Oct 17, 2024
c092fb8
[CPU] Improve instruction generating algorithm for pow(a, large_N) (#…
xuchen-intel Oct 17, 2024
b3c3d3b
Throws ov::Cancelled to uplevel instead of ov::Exception (#26962)
xufang-lisa Oct 17, 2024
e4ce1bb
Bump actions/cache from 4.0.2 to 4.1.1 (#26964)
dependabot[bot] Oct 17, 2024
6198275
[GPU] Added tests for LoRA with empty adapters and handling of incorr…
Lyamin-Roman Oct 17, 2024
675dc6e
[CPU]support glm4 rope (#27094)
zhangYiIntel Oct 17, 2024
487b391
[PyOV] Extend Python API with SliceScatter-15 (#27090)
mmikolajcz Oct 17, 2024
a356945
Details: (#27008)
pravin25 Oct 17, 2024
6644fc8
[Spec]: Added initial specification of Searchsorted op (#26887)
pkowalc1 Oct 17, 2024
6dbca1f
NPUW: Disable AVX2 code with ENABLE_AVX2=OFF (#26890)
eshiryae Oct 17, 2024
54db50b
[GPU] Fix weight reorder src format to avoid inconsistency ndims of s…
wilson-seok Oct 17, 2024
2f62be0
[CPU] Support different Key/Value head size and not multiples 16 of h…
luo-cheng2021 Oct 17, 2024
28bb0fd
[PT FE] Handle None-value case among inputs (#27102)
rkazants Oct 17, 2024
55d8c47
Update setuptools requirement from <74.1.0,>=65.6.1 to >=65.6.1,<75.3…
dependabot[bot] Oct 17, 2024
8822480
#20927 support inputs that have no batch (#26778)
tianyiSKY1 Oct 17, 2024
212be8e
NPUW: Dynamic Spatial (#27104)
dmatveev Oct 18, 2024
ac7cb8b
[GPU] Save use_onednn attribute in the blob (#27097)
Oct 18, 2024
4bf52c1
[GPU] Fix USMHost tensor sharing between models from different Cores …
Oct 18, 2024
939b35a
[NPU]Change NPUBackend log (#27073)
DanLiu2Intel Oct 18, 2024
a8293f3
Bump actions/upload-artifact from 4.4.0 to 4.4.3 (#27113)
dependabot[bot] Oct 18, 2024
e582f61
[Transformations] Fix exception when converting precision on Read_Val…
luweizhou2016 Oct 18, 2024
43df0b6
TorchFX: GPTQ accuracy fix (#26294)
cavusmustafa Oct 18, 2024
56fe26f
Introduce protopipe (#27087)
Maxim-Doronin Oct 18, 2024
03c9ae3
[GPU] Removed redundant part for dump file name (#27123)
e-ddykim Oct 18, 2024
373cf90
[GHA] Enable thread sanitizer (#26634)
mryzhov Oct 18, 2024
5a65547
[TESTS] Fix version for huggingface_hub (#27126)
mvafin Oct 18, 2024
62183ab
[DOCS] Moved versioning to repo (#27128)
akopytko Oct 18, 2024
0648cd0
[PT FE] Fix sym GPTQ pattern to have consistent graph (#27037)
mvafin Oct 18, 2024
8c36c00
[CORE] Skip unnecessary convert_to_supported_precision if ConstantFol…
itikhono Oct 18, 2024
13becaa
[TESTS] Print test names in log (#27121)
mvafin Oct 18, 2024
f33e255
[TFL FE] Export public API symbols for TFLite Delegate (#27140)
rkazants Oct 18, 2024
c5025cc
[TRANSFORMATIONS] Introduce a new method of testing SDPAToPA transfor…
CuriousPanCake Oct 19, 2024
9a02e54
[JAX FE] Support lax.argmax operation for JAX (#26671)
halm-zenger Oct 20, 2024
2be7e5f
[GPU] Fix fused op macro for dynamic shape eltwise fusing into convol…
wilson-seok Oct 21, 2024
d0056bd
[CPU][ARM] Enable fast math in ACL deconvolution executor (#26615)
alvoron Oct 21, 2024
0064022
fix the coverity (#26963)
azhai219 Oct 21, 2024
96595eb
Bump actions/upload-artifact from 4.4.0 to 4.4.3 (#27151)
dependabot[bot] Oct 21, 2024
9ea3bea
[TESTS] Fix retry mechanism to raise if retry didn't help (#27139)
mvafin Oct 21, 2024
ebdf1fc
[CPU] Fuse SDPA before/after Reshape+Transpose Node to SDPA (#26819)
xipingyan Oct 21, 2024
4043e15
[PyOV] Extend Python API with STFT-15 (#27142)
mitruska Oct 21, 2024
3f953f4
[DOCS] benchmark content restructuring (#26918)
kblaszczak-intel Oct 21, 2024
dd16602
[GPU] Weightless caching (#25731)
tkrupa-intel Oct 21, 2024
f391161
[DOCS] torch.compile examples (#27107)
kblaszczak-intel Oct 21, 2024
308b420
[GPU] Fix different element types of MatMul dequantization scales iss…
yuanxion Oct 21, 2024
2cb8222
[CPU] Use actual input shape to init desc for MemoryInputSDPA (#27143)
EgorDuplensky Oct 21, 2024
b785e6e
[GPU] Enable dynamic quantization gs32 as default for non-systolic (#…
isanghao Oct 21, 2024
2e25c87
[GPU] Fix not to check _dynamic_dims_mask when get_from_padded_pool()…
wilson-seok Oct 21, 2024
3439873
[GPU] Disable onednn pool in some cases due to the bug (#27115)
Oct 21, 2024
924b311
[Conan Build]Fix Debug Build (#27150)
CaptainNeil Oct 21, 2024
c9deb21
[IR FE] Ignore unrecognized xml rt_info entries (#27118)
t-jankowski Oct 21, 2024
a3c07d5
[GPU] Added empty LoRA adapters support for onednn case (#27111)
Lyamin-Roman Oct 21, 2024
85253c4
[ONNX] Update ONNX version for vcpkg (#27155)
gkrivor Oct 21, 2024
1f41cba
Update NNCF WC documentation (#27101)
l-bat Oct 21, 2024
d34cdda
[NPUW] Support mixed precision models (#27130)
smirnov-alexey Oct 21, 2024
5f4a445
[CPU] CACHE_DIR hash optimization (#25624)
nshchego Oct 21, 2024
8a33df7
Added i8 for DQMatMulCwi (#27112)
AsyaPronina Oct 21, 2024
de0dc71
[ONNX] Direct loading from ModelProto object (#27124)
gkrivor Oct 22, 2024
d6dc495
[PT FE] Fix aten.index.Tensor for indices with None values (#27122)
rkazants Oct 22, 2024
e3ad821
[CPU] Implemented "jit_exp_emitter" (#26974)
a-sidorova Oct 22, 2024
adeb3d2
Adding CODE_OF_CONDUCT.md (#27100)
moslex Oct 22, 2024
28e1c82
[CPU][ARM] ACL upgrade to v24.09 (#26852)
alvoron Oct 22, 2024
a02da92
Docs rename ovcategory in sitemap (#27177)
akopytko Oct 22, 2024
1cde010
[DOCS] port (#27192)
akopytko Oct 22, 2024
5ac9eda
[tests] MSVC debug asserts on vector iterators incompatible in test (…
praasz Oct 22, 2024
5a396e6
[TF FE] Skip one test case for keras Embedding on CPU due to timeout …
rkazants Oct 22, 2024
2fc59f5
Use wzp u8 type and bugfix for FC dyn-quan (#26816)
byungilm Oct 23, 2024
f5dc4f5
[PyOV] update numpy <2.2.0 (#27176)
akuporos Oct 23, 2024
121917a
support new isa avx2_vnni_2 in threading scheduling (#27194)
wangleis Oct 23, 2024
93379b5
[CI] [GHA] Update list of workflows for rerunner, add step for statis…
akashchi Oct 23, 2024
56a0dca
[TRANSFORMATIONS] Move print_model transformation to transformation's…
CuriousPanCake Oct 23, 2024
a852c4a
[OV JS] Perform inference in electron app in nodejs e2e test (#27131)
vishniakov-nikolai Oct 23, 2024
c375336
[NPU][ov_integration] Skip BF16 tests (#27168)
sbutnari Oct 23, 2024
5676ff8
[NPU] Separate the compiler headers from the runtime headers (#27125)
pereanub Oct 23, 2024
dfa6235
[DOCS] tiny img fix mstr (#27202)
kblaszczak-intel Oct 23, 2024
c5e16fc
[PT FE] Support aten::atan2 for pytorch models (#27026)
tiebreaker4869 Oct 23, 2024
1b4795e
[PT FE] Save args on meta device when patching (#27167)
mvafin Oct 23, 2024
82eac02
[GPU] Dynamic quantization fix for systolic case (#27187)
isanghao Oct 23, 2024
75bbdf0
[CPU]: Added impl of SearchSorted op (#27036)
pkowalc1 Oct 23, 2024
1b0a4cf
[PyOV] Migrate wheel building interface to `python -m build` for main…
p-wysocki Oct 23, 2024
a979f96
[DOCS] conformance report update mstr (#27200)
kblaszczak-intel Oct 23, 2024
2dd8447
[DOCS] Updating Interactive Tutorials (#27205)
sgolebiewski-intel Oct 23, 2024
b67456f
[TESTS] Skip signature test for older torch (#27165)
mvafin Oct 23, 2024
5e5c987
[NPU] Add pfn build log to pfn-related function (#26772)
ShaojieZhuIntel Oct 23, 2024
ca926d6
[Do not merge][GPU] Update onednn to 3.7pc (#26943)
yeonbok Oct 23, 2024
6458855
[PT FE] Report about FakeTensor during conversion (#27203)
rkazants Oct 23, 2024
f4e8b82
[GPU] Optimize iGPU FC with prime number batch size (#24893)
riverlijunjie Oct 23, 2024
97b20c9
[auto] Fix time calculation when time points lists are empty (#27199)
praasz Oct 24, 2024
cbeb131
[Transformations] Add SliceScatter-15 decomposition transformation (#…
mmikolajcz Oct 24, 2024
60a8efd
[CPU][OMP] Fix for Interpolate node (#27184)
nshchego Oct 24, 2024
f9406ad
[CPU] fix strided_slice with new axis (#27103)
azhai219 Oct 24, 2024
c202882
[GPU] Enable fusing dynamic eltwise with gemm in onednn case (#27193)
Lyamin-Roman Oct 24, 2024
dd55426
Bump actions/checkout from 4.1.7 to 4.2.2 (#27214)
dependabot[bot] Oct 24, 2024
27780a6
Revert "[GPU] Increasing conditions for using fake_aligned shapes (#2…
Lyamin-Roman Oct 24, 2024
2a9c69d
[RISCV64] add nhwc layout support for eltwise executor (#26531)
BHbean Oct 24, 2024
17f1601
[GPU][TESTS] Fix weightless caching tests (#27163)
tkrupa-intel Oct 24, 2024
65a8f39
[intel-npu] Implementing LUID property in npu plugin (#27091)
csoka Oct 24, 2024
de66f0e
[GPU] Handle runtime scale value for PagedAttention (#27204)
sshlyapn Oct 24, 2024
d96bd7d
[Transformations] Fix vector subscript out of range in transformation…
praasz Oct 24, 2024
ea04212
[Core/Ref] Multiclass NMS: Fix vector initialization (#27157)
t-jankowski Oct 24, 2024
6a8a69c
[Pytorch fronted]: Added support for Search Sorted op (#26976)
pkowalc1 Oct 24, 2024
3c0005e
[DOCS] Adding GenAI Use Cases (#27062)
sgolebiewski-intel Oct 24, 2024
8faeed1
[PyOV] Extend Python API with SearchSorted-15 (#27230)
mmikolajcz Oct 24, 2024
104fe03
Add opencv config (#27164)
Maxim-Doronin Oct 24, 2024
9b377f4
[TESTS] Remove unused requirements.txt (#27235)
mvafin Oct 24, 2024
433e44e
[NPUW] Add Slice before last MatMul (#27229)
smirnov-alexey Oct 24, 2024
79b0bad
Fixed vcpkg Android ARM64 build with ONNX 1.16.2 (#27217)
ilya-lavrenov Oct 24, 2024
65e9413
Check input shape with '_output_shapes' attribute if tf model unset '…
a3213105 Oct 25, 2024
59f2eb0
Merge branch 'hybridchecker' into fix_tf_fe_input_shape
a3213105 Oct 25, 2024
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.
1 change: 0 additions & 1 deletion .github/ISSUE_TEMPLATE/bug.yml
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,6 @@ body:
- Caffe
- ONNX
- PyTorch
- mxnet
- PaddlePaddle
validations:
required: false
Expand Down
63 changes: 62 additions & 1 deletion .github/actions/cache/__tests__/cleanup.test.js
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,12 @@ const getInputMock = jest.spyOn(core, 'getInput').mockImplementation();
const setFailedMock = jest.spyOn(core, 'setFailed').mockImplementation();

const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'test-cleanup-'));
const cacheRemotePath = path.join(tempDir, 'cache_remote');
const cacheRemotePath = path.join(
tempDir,
'subdir_1',
'subdir_2',
'cache_remote'
);

const cacheFiles = ['cache_1.cache', 'cache_2.cache', 'cache_3.cache'];
const minAccessTime = 7 * 24 * 60 * 60 * 1000; // 1 week
Expand Down Expand Up @@ -283,4 +288,60 @@ describe('cleanup', () => {
// check that sub directory exists
expect(fs.existsSync(cacheSubPath)).toBe(true);
});

it('Cleanup directory with subdirectories and files (recursive=true)', async () => {
const cacheSubPath = path.join(tempDir, 'subdir_1');
// Set the action's inputs as return values from core.getInput()
getInputMock.mockImplementation(name => {
switch (name) {
case 'cache-path':
return cacheSubPath;
case 'restore-keys':
return 'cache';
case 'cache-size':
return 1;
case 'recursive':
return true;
default:
return '';
}
});

await cleanupImpl.cleanUp();

expect(runMock).toHaveReturned();
// cache2 and cache3 should be removed
for (const cache of cacheFiles.slice(1, 2)) {
expect(fs.existsSync(path.join(cacheRemotePath, cache))).toBe(false);
}
// check that file1 exists
expect(fs.existsSync(path.join(cacheRemotePath, cacheFiles[0]))).toBe(true);
});

it('Cleanup directory with subdirectories and files (recursive=false)', async () => {
const cacheSubPath = path.join(tempDir, 'subdir_1');
// Set the action's inputs as return values from core.getInput()
getInputMock.mockImplementation(name => {
switch (name) {
case 'cache-path':
return cacheSubPath;
case 'restore-keys':
return 'cache';
case 'cache-size':
return 1;
case 'recursive':
return false;
default:
return '';
}
});

await cleanupImpl.cleanUp();

expect(runMock).toHaveReturned();
// cache2 and cache3 should be removed
for (const cache of cacheFiles) {
expect(fs.existsSync(path.join(cacheRemotePath, cache))).toBe(true);
}
});
});
6 changes: 5 additions & 1 deletion .github/actions/cache/__tests__/save.test.js
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,11 @@ describe('save', () => {

it('Cache files: absent remote cache dir', async () => {
// Set the action's inputs as return values from core.getInput()
const cacheRemotePathAbsent = path.join(tempDir, 'cache_remote_absent');
const cacheRemotePathAbsent = path.join(
tempDir,
'cache_remote_absent',
'subdir'
);
getInputMock.mockImplementation(name => {
switch (name) {
case 'cache-path':
Expand Down
4 changes: 4 additions & 0 deletions .github/actions/cache/cleanup/action.yml
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,10 @@ inputs:
evicted to limit the total cache storage'
default: 50
required: false
recursive:
description: 'Scan the current directory only or all subdirectories'
default: false
required: false

runs:
using: 'node20'
Expand Down
Loading