You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by la...@apache.org on 2020/11/02 17:05:15 UTC
[incubator-mxnet] branch leezu-patch-1 updated (f654240 -> 254a4cd)
This is an automated email from the ASF dual-hosted git repository.
lausen pushed a change to branch leezu-patch-1
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git.
discard f654240 Update to Intel(R) Math Kernel Library 2020 Update 1
discard 5ea52ee Fix linking gnu omp when intel omp should be linked
discard a61737b Merge branch 'master' into leezu-patch-1
discard 556e9cf Disable MKL_USE_STATIC_LIBS by default
add 54c0155 User Feedback Widget (#18639)
add b4b8b80 Gluon.probability (#18403)
add 348ab4d fix broken installation widget - remove empty entries (#18661)
add beafba7 [Improvement] Invoke mkldnn and cudnn BatchNorm when axis != 1 (#18504)
add a9b16f7 change bn test (#18688)
add 19e373d Fix scipy dependency in probability module (#18689)
add 9c5b95a Partition API adding and deleting new params to Block and Symbol (#18405)
add 8ebb537 add 'needs triage' label to new bug reports (#18696)
add 9d62392 Fix python micro-site table of content bugs (#18664)
add 7f7e1c5 Add better partial args/aux handling in symbol optimize_for (#18350)
add 7c9c4fc Merge content from numpy.mxnet.io into mxnet official website (#18691)
add f125f5f Fix all anchor shifts on website (#18674)
add d8430b6 Set CMAKE_CUDA_COMPILER in aarch64-linux-gnu-toolchain.cmake (#18713)
add d512814 Disable test coverage in MKL builds (#18443)
add 0dc30a2 Enable GPU Memory profiler tests (#18701)
add 12ec046 Migrate from private to public jetson toolchain files (#18677)
add e2366e9 Refactor scope functionality in Python API (#18619)
add 6901325 Add the newest mxnet discuss version. Add d2l.ai (#18663)
add 8198442 [numpy] symbolic advanced indexing (#18319)
add 37bdf0b [MXNET-1453] Support the intput whose dimension is greater than 6 for Transpose and Rollaxis (#18707)
add 2abf0b8 Initialize docker cache in build.py for docker-compose containers (#18724)
add 3ef00b8 Refactoring of Pooled Storage Manager classes (#18582)
add a77f774 Remove NNPACK integration (#18722)
add 60d0672 Add qr backward for wide matrices with m < n (#18197)
add 3e0df1b Disable sparse op test (#18741)
add cec86ad Move gluon.metric api docs (#18733)
add 444a7ee Revert "Add qr backward for wide matrices with m < n (#18197)" (#18750)
add 146b49e Unittest tolerance handling improvements (#18694)
add bf26bcc [NumPy] enable large tensor in np (#18368)
add 1aec483 Add qr backward for wide inputs ncols>nrows (#18757)
add a7c6606 Remove Makefile build support (#18721)
add 6bb3d72 Improve test seeding in test_numpy_interoperablity.py (#18762)
add 9548b0c Remove duplicate settings in .codecov.yml (#18763)
add a330a02 Fix mx.symbol.numpy._Symbol.__deepcopy__ logic error (#18686)
add 1928117 Fix crash when accessing already destructed static variables (#18768)
add 18af71e CI: Migrate remaining Dockerfiles to docker-compose.yml and remove unused code (#18771)
add 02ae456 Improve environment variable handling in unittests (#18424)
add e31ad77 set website default version to current stable (1.6) version (#18738)
add 06b5d22 ONNX import: use Conv pad attribute for symmetrical padding (#18675)
add 2fbd182 Split up CI sanity test functions to enable fine-grained trigger (#18786)
add c1db2d5 Remove caffe plugin (#18787)
add 98b3f73 add support for np.ndarray in autograd.function (#18790)
add 9e77e81 Update CUB and include it only for CUDA < 11 (#18799)
add 74430a9 remove NLL in metric (#18794)
add a807f6d [NumPy] loss for np array (#17196)
add 7908d7e [numpy] fix flaky mixed precision binary error (#18660)
add f83dbac remove executor manager from API doc (#18802)
add 126636c Fix naming in runtime_functions.sh (#18795)
add e9829e7 Cherry-pick large tensor support from #18752. (#18804)
add 915f6b4 Remove deepnumpy reference and move Numpy tutorials to top level (#18798)
add 9308aca remove other language bindings section from website api page (#18783)
add b685fad use regex that is supported by all browsers (#18811)
add 6bbd531 Update clang-tidy integration (#18815)
add 608afef Fix dirichlet flaky tests (#18817)
add 045efb2 [NumPy] DLPack refactor and npx.from_numpy (#18656)
add aa53291 add adaptive left margin for python site document body (#18828)
add 7a24006 Enable DIST_KVSTORE by default in staticbuild (#18796)
add ac36089 Fixup move gluon.metric api docs (#18748)
add 08a5ee3 fix gelu to use erf based algorithm (#18827)
add 5a22193 [NumPy] allow mixed array types (#18562)
add 51340d8 Add compiled_with_cxx11_abi API (#18836)
add 54b9e9c remove unnecessary usage of pretrained models, and prefer smaller size (#18844)
add 9fd2cce Update tests/README.md Docker instructions to match ci/README.md (#18848)
add 534cdbc Create greetings.yml (#18842)
add 7a5a488 Fix broken link in docs/README.md (#18847)
add 4bb8224 Fixed python website double scroller and improve UX (#18845)
add f872b43 Protobuf_USE_STATIC_LIBS must be set on Apple too (#18851)
add 7f2e314 update setup.py (#18850)
add 95fa63f Update the onnx-tensorrt submodule - CI to TRT7 (#18574)
add 7a40219 Remove check for subgraph with cycles (#18555)
add b8eccc8 fix set default website version rewrite rule for cdn (#18856)
add 2e97226 Fix edge case when casting gluon Block before export (#18853)
add 59e200a fix nn.dense doc (#18830)
add 7b7cef5 MXNet-TRT: Add PrePartition param caching - move init_tensorrt_params logic (#18490)
add 0f65ef6 nb fix (#18858)
add a78f137 improve python api website ux - make toc sticky (#18863)
add 84f8984 ElementWiseSum fix for oneDNN (#18859)
add a3eabf0 Fix MXLibInfoCompiledWithCXX11ABI (#18864)
add d101c3c Add SOVERSION when build shared libmxnet.so library (#17815)
add 708a900 Fix a bug in MXNet-TensorRT (#18870)
add 1694d2f [CI] remove data.mxnet.io usage for CI stability (#18871)
add dde635f Re-enable the linker version scripts for binary distribution (#18872)
add d5fdcbf drop list support for gluon trainer (#18877)
add cf908fd [Numpy][Bugfix] Add hybridization test to loss layers (#18876)
add 706c369 fix trainer when the model involves share_parameters (#18880)
add d52d9c6 Revert "Add SOVERSION when build shared libmxnet.so library (#17815)" (#18882)
add 5c50475 fix pooling_convention warning when convert model to onnx (#18529)
add d0e17e5 [Numpy] FFI: sort, argsort, vstack etc (#17857)
add e101d68 [Gluon] Add VAE demo (#18758)
add 016c166 remove upper bound (#18857)
add f2a8b97 Remove manually created symbolic link to ninja-build (#18906)
add 83d2af5 Gamma reparameterization gradient (#18852)
add e2cbf66 Revert "drop list support for gluon trainer (#18877)" (#18892)
add a2b400c fix center element not being copied (#18917)
add 344587f Safe accumulation for computing gradient in Embedding & Take (#18385)
add ee80b77 Fix default CPU allocator memory alignment (#18885)
add 86e96dc Fix backward of arctan2 and rarctan2 scalar on GPU (#18440)
add daf8b43 Support extra inputs for subgraph ops (#18779)
add be12c8d [Website] adjust website structure (#18839)
add 2610c10 Change Partition API's options_map to std::unordered_map (#18929)
add e06ee4e Faster GPU frozen BatchNorm (#17368)
add 0afeb97 Fix instancenorm math equation (#18955)
add c789d02 Fix Python docs (#18924)
add 32994bb Fix setting cudnn bias stride (#18905)
add 8794a0a Numpy Dot Large Tensor Fix (#18925)
add c09bbc1 Fix Horovod build error due to missing exported symbols (#18958)
add 22d69ef Get rid of monkey patching in LossScaler overflow handling (#18959)
add 50312af turn on MXNET_SAFE_ACCUMULATION by default (#18961)
add 69ec338 Numpy Ops Large Tensor Tests (#18932)
add 5e408bc add ffi (#18868)
add adcd997 CI: Remove nccl installation after upstream fix (#18965)
add bbc39fa add signal handler for fpe, bus error (#18956)
add 29d6f27 Use RTC for elementwise and broadcast ops (#18622)
add 20957ff Numpy Ops Large Tensor Tests Batch 2 (#18968)
add 9bdd4d6 fix #18927 (#18972)
add 4a7282f fix #18933 (#18974)
add a847df7 Fixing tvmgpu issue & not restoring tvmop checks (#18818)
add 46c0fb3 Numpy Random Ops Large Tensor Fix (#18976)
add 72eff9b Reducing the number of calls of the NDArray constructors (#18570)
add 0de7484 clean up C API (#18969)
add 3c4ac19 Fix LeakyRelu behaviour on empty input (#18934) (#18996)
add 8be953f Fix isnan usage in RTC (#18984)
add b2c736f [numpy] fix logical ops gpu build (#18983)
add 566bbf7 Numpy Random Ops Fix & Testcases (#19004)
add 49cc229 fix doc for SigmoidBinaryCrossEntropyLoss (#19010)
add 8245fe2 Fix numpy equal broadcast (#19008)
add 998c6ce Numpy Gather ND Large Tensor fix (#18981)
add 6b59605 Numpy Pooling and ROI Pooling Large Dimension Checks (#19013)
add a9ca660 [COMMUNITY] remove mentions of JIRA, update community docs (#18992)
add 29c90ee Support for fp16 in SpM x DnsM on GPU (#18930)
add 48c2198 Add size check for numpy ctc loss (#19028)
add b0c39f7 Update basic_layers.py (#19038)
add eeb6f34 [CI] use fixture to reduce download of cifar10 (#19039)
add a3115d5 [DOC] update contributors and readme (#19041)
add ea3235e switch pip doc to markdown (#19037)
add 74edcde add .asf.yaml for enabling wiki (#19042)
add e2aacce Fix fusion of clip if a_min or a_max are not given (#19035)
add 1393602 [MXNET-1446] Quantization: intgemm matrix multiply wrappers (#17559)
add 309b39a _slice_assign and _slice_assign_scalar large tensor fix (#19032)
add 89e48d4 Numpy nonzero large tensor fix (#19015)
add ddb798a Numpy RNN operator large dim checks (#19033)
add de34763 set_lower_bound(1) so that stride is not zero (#18997)
add 9b22c8c Stop packaging GPL libquadmath.so (#19053)
add af467d2 Fix the error of gradient of np.pad (#19044)
add 9268f89 Numpy pick large tensor fix (#19025)
add 8379740 MXNet Extensions enhancements2 (#19016)
add 5122d32 fix block.export (#17970)
add 4cfb9e1 Fix MNIST classification example (#19072)
add f2e90a2 Update NEWS, README and website for 1.7.0 (#19047)
add ddfd9e4 Resolve minor docs issues (#19062)
add f732530 [FEATURE]Enable large tensor support for batch flatten (#19063)
add 45bfb83 Update .htaccess (#19079)
add bb7e0cb Fix binary broadcast shape large tensor (#19070)
add 363caac Add build config for darwin native distribution (#19083)
add af2b4bc [API] clean up gluon contrib (#19046)
add 23b3665 [COMMUNITY] display github discussions link in issues (#19090)
add 62b7f03 Assure NDArray.reshape does not change the array size (#19078)
add 5a99105 [DOC] enable edit on github (#19040)
add 7e97627 Fix typo in ISSUE_TEMPLATE config.yml (#19093)
add c1eaada Update requirements (#19061)
add 04e394a update runtime setting default values (#18987)
add 5afb4b1 enable dnnl primitive cache (#17891)
add 40a2a52 Use chain.from_iterable in 2 modules (#18606)
add 3ba9ffd [COMMUNITY] Add mention of mirroring of RFC issues to dev@ (#19092)
add 0c0457a Add a contrib operator for dynamic reshape (#15872)
add 5b7a6d9 Re-enable the test_gpu_memory_profiler_gluon test case (#18704)
add 45952e2 Make C Runtime API a C API again (#19085)
add 6b01dc2 Fix for duplicate subgraph inputs/outputs (#16131)
add 131fa69 Fix default context handling in Gluon 2 (#19113)
add 95e1814 [PIP] add build target in cmake for osx compat (#19110)
add e5a7814 Improve createOpState for custom ops (#19103)
add d144f3b add v1.7 website entries to general version dropdown (#19116)
add 1f15819 Fix race condition in NaiveEngine::PushAsync (#19108)
add 3240e1e set v1.7 as default website version (#19120)
add 856e255 add Ciyong Chen as a new committer (#19115)
add 5c1aadc Add cmake flag USE_FATBIN_COMPRESSION, ON by default for CUDA >= 11 (#19123)
add f1acda7 Update setup.py for darwin builds (#19130)
add 6cbdfa5 Elemwise binary op backward fix (#19106)
add 0e29280 add Jackie Wu as a new PPMC member (#19136)
add 2697573 updated version (#19134)
add 179262b Fix legacy codepath detection feature for decorated HybridBlocks (#19143)
add 11e1c0b Fix comment and cmake variables and search paths in FindMKL.cmake (#19152)
add db07b7e Update README.md (#19145)
add ec62fcf [Submodule] Upgrade to oneDNN v1.6.3 (#19153)
add 0b638fe add DOAP (#19146)
add adbc17b Switch to GCC 8 for distribution build (#19034)
add 30ae04a SymbolBlock.imports ignore_extra & allow_missing (#19157)
add 25ab7a6 Fix "Re-enable the test_gpu_memory_profiler_gluon test case" (#19154)
add bf08ab0 Revert "Switch to GCC 8 for distribution build (#19034)" (#19179)
add ca87cbf Opt in to newer GCC C++ ABI on RedHat Developer Toolset (#19182)
add eaa3d73 add Manu Seth as a new committer (#19191)
add a563ae3 Fix intgemm flaky test in #19197 for master (#19202)
add dd44c0c Fix numpy ndarray `__getitem__` for HybridBlock.forward usecase (#19171)
add 42ef1cb Add cmake flag USE_FATBIN_COMPRESSION, ON by default (#19175)
add d7fc49e [COMMUNITY] Add Przemek Tredak as a new PPMC member (#19205)
add b910578 Check for version artifacts in website pipeline (#19210)
add bd0846a [BUGFIX] Pip Build: use runtime.Features instead of manual check for mkldnn headers (#19195)
add b225fa5 Python level HybridBlock export API (#19220)
add 4a8da9e [BUGFIX]Fix cuDNN dropout reproducibility (#19209)
add 991e206 added key for samskalicky (#19223)
add d816929 [WEBSITE] publish master website to /versions/master (#19190)
add 8e9877b fix master website version null foler (#19237)
add 7dcfedc Update qr backward documentation (#19243)
add 9de2a48 [Numpy] Tensordot Gradient Fixed (#19187)
add 464608c fix python 3.8 ctypes dll load with windows (#19236)
add 5dc6cad Add dedup flag to master from #19112 (#19246)
add 2d3ce93 CI: Add docker containers with Cuda 11.0. (#19219)
add 39ea683 AMP support for Numpy ops (#19036)
add 7d3e027 Fix for optimize_for multiple subgraph properties issue (#19263)
add e297471 Update Jenkinsfile_utils.groovy (#19284)
add a1c5d97 [Numpy] Support `mxnet.numpy.ndarray.diagonal()` (#19285)
add 7567ff5 Update Jenkinsfile_utils.groovy (#19288)
add 906a159 DOC - Fix typos (#19289)
add 761a339 Enable clang-tidy performance rules (#19226)
add 99466f6 Skip flaky test_gpu_memory_profiler_gluon (#19250)
add af5dd69 Update github bug report template (#19287)
add 58e3d7f Exclude symbols from statically linked third-party libraries (#19241)
add 3c5beb3 Switch to GCC 8 for distribution build (#19185)
add 48a1fbf Limit the number of ElementWiseSum kernels compiled by RTC (#19266)
add 3042df0 Enable CUDA 11.0 on nightly development builds (#19295)
add db171a8 [submodule] Upgrade oneDNN to v1.6.4 (#19292)
add 7c61b4b Record np_reshape instead of Reshape in np mode (#19293)
add a6fb7c2 Porting: Fixed setting attributes in reviewSubgraph (#19277)
add e67d53e Einsum cutensor GPU (#18921)
add 45c933b enable LTS for np cumsum operator (#19297)
add 95f5cc6 Numpy large tensor tests batch 3 (#19059)
add c2d56dc [BUGFIX] [Numpy] MXNet fp16 initialization bug #19118 (#19270)
add 4867b4e remove arch3.0 from cu110.cmake (#19309)
add 510900f Numpy polyval large tensor fix (#19306)
add 562c69e update ci/build_windows.py MKLROOT and readme (#19160)
add 9f8af7b enable LTS for numpy round and around (#19300)
add 14d51a9 Numpy roll large tensor fix fix (#19301)
add b6ab781 Enable large tensor support for numpy cross (#19312)
add a43af5b Fix possible IMA in amp_multicast fusion (#19318)
add 9c90128 enable large tensor support for array_split (#19303)
add 480d027 Remove duplicate setup and teardown functions (#19254)
add 16eb89b Add GPU-optimization for split op (#19131)
add 4dc9947 BUGFIX Updated the auto-encoder example. Fixes #18712 (#19321)
add 5ed72b1 Fix python API doc and all rst warnings for sphinx website build (#19329)
add 293fd9a [DOC] Add examples of running Python unittests to docs (#19253)
add 191341f change int to index_t (#19326)
add ce37302 Numpy vstack large tensor fix (#19313)
add 94b649f BUGFIX Fix ConvTranspose __repr__ (#19338) (#19344)
add 93ddbbf Numpy diag large tensor fix (#19302)
add ce1e682 Add FindCUTENSOR.cmake (#19334)
add d0ceecb [DOC] Add shield for pr-awaiting-review and link to codereview page (#19352)
add 7bbe928 adding large tensor tests to verify support for split, hsplit, vsplit, dsplit (#19357)
add dfda45b fix seg fault (#19324)
add e6cea0d fix numpy ediff1d large tensor (#19310)
add a0fd1fe Faster pointwise fusion graph pass (#19269)
add defaafe Fix AtWithRecord (#19374)
add 3faf6df Numpy nan_to_num large tensor fix (#19350)
add 75c6216 Numpy Argmax Rewrite (#19339)
add 9e9f972 Move AMP from contrib to core (#19347)
add 43750c8 Remove cleanup on side threads (#19378)
add 3f833e1 Numpy histogram large tensor fix (#19392)
add 3f436fb Remove duplicate @with_seed decorators (#19336)
add eed080f argmin optimization (#19404)
add 187c75d Enable large tensor support for interp (#19363)
add 8e5a16c More extensions fixes (#19393)
add 3dda8e9 Enable large tensor support for padding (#19403)
add 9bfe311 Update elemwise_binary_broadcast_op_basic.cu (#18761)
add 329aebd initial disclaimer update (#19402) (#19416)
add 95f9ea2 fix (#19376)
add 4b3be14 Fix windows dll loading for compute capabilties >7.5 (#19410)
add 8dc3652 Add option to build with shared c runtime on windows (#19409)
add f9fef4d [LICENSE] Change intgemm to a submodule instead of fetch. (#19408)
add bd55002 fix (#19366)
add 383f8d1 fix fill_diagonal against large tensors (#19429)
add c6c5e4b Numpy diff large tensor fix (#19365)
add 0743fc2 Update oneDNN to v1.6.5 (#19444)
add 0514233 [TUTORIAL] Update crashcourse for MXNet 2 (#19345)
add 0faecf0 [BUGFIX] Fix MKLDNN BatchNorm with even number of channels (#19150) #19299 (#19425)
add cec6bcf operators for the sliding window self-attention (#19387)
add e486704 Mark test_foreach as garbage_expected (#19459)
add 2df5929 Disable MKL_USE_STATIC_LIBS by default
add f20375a Fix linking gnu omp when intel omp should be linked
add 254a4cd Update to Intel(R) Math Kernel Library 2020 Update 4
This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version. This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:
* -- * -- B -- O -- O -- O (f654240)
\
N -- N -- N refs/heads/leezu-patch-1 (254a4cd)
You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.
Any revisions marked "omit" are not gone; other references still
refer to them. Any revisions marked "discard" are gone forever.
No new revisions were added by this update.
Summary of changes:
.asf.yaml | 15 +
.clang-tidy | 58 +-
.codecov.yml | 5 -
.github/ISSUE_TEMPLATE/bug_report.md | 17 +-
.github/ISSUE_TEMPLATE/config.yml | 13 +-
.github/ISSUE_TEMPLATE/rfc.md | 18 +
.github/PULL_REQUEST_TEMPLATE.md | 15 +-
.github/workflows/greetings.yml | 20 +
.gitignore | 2 +
.gitmodules | 3 +
3rdparty/intgemm | 1 +
3rdparty/mkldnn | 2 +-
3rdparty/mshadow/CMakeLists.txt | 3 +
3rdparty/mshadow/mshadow/base.h | 59 +-
3rdparty/mshadow/mshadow/cuda/tensor_gpu-inl.cuh | 77 +
3rdparty/mshadow/mshadow/dot_engine-inl.h | 24 +-
3rdparty/mshadow/mshadow/half2.h | 162 --
3rdparty/mshadow/mshadow/stream_gpu-inl.h | 61 +-
3rdparty/mshadow/mshadow/tensor.h | 26 +
3rdparty/mshadow/mshadow/tensor_cpu-inl.h | 33 +
3rdparty/mshadow/mshadow/tensor_gpu-inl.h | 8 +
3rdparty/nvidia_cub | 2 +-
3rdparty/onnx-tensorrt | 2 +-
CMakeLists.txt | 278 ++-
CONTRIBUTORS.md | 168 +-
DISCLAIMER-WIP | 7 +-
KEYS | 59 +
LICENSE | 39 +
Makefile | 768 -------
NEWS.md | 815 +++++--
README.md | 157 +-
benchmark/opperf/utils/profiler_utils.py | 2 +-
benchmark/python/ffi/benchmark_ffi.py | 11 +-
cd/Jenkinsfile_cd_pipeline | 2 +-
cd/Jenkinsfile_release_job | 2 +-
cd/README.md | 5 +-
cd/mxnet_lib/static/Jenkins_pipeline.groovy | 4 +-
cd/python/pypi/pypi_package.sh | 2 +-
cd/utils/artifact_repository.md | 6 +-
cd/utils/mxnet_base_image.sh | 9 +-
cd/utils/test_artifact_repository.py | 14 +-
ci/Jenkinsfile_docker_cache | 1 -
ci/Jenkinsfile_utils.groovy | 12 +-
ci/build.py | 187 +-
ci/build_windows.py | 10 +-
ci/dev_menu.py | 5 +-
ci/docker/Dockerfile.build.centos7 | 53 +-
ci/docker/Dockerfile.build.jetson | 43 +-
ci/docker/Dockerfile.build.ubuntu | 79 +-
ci/docker/Dockerfile.build.ubuntu_cpu_c | 35 -
ci/docker/Dockerfile.build.ubuntu_cpu_jekyll | 43 +-
ci/docker/Dockerfile.build.ubuntu_cpu_julia | 66 -
ci/docker/Dockerfile.build.ubuntu_cpu_lite | 45 -
ci/docker/Dockerfile.build.ubuntu_cpu_python | 46 -
ci/docker/Dockerfile.build.ubuntu_cpu_r | 46 -
ci/docker/Dockerfile.build.ubuntu_cpu_scala | 53 -
ci/docker/Dockerfile.build.ubuntu_gpu_tensorrt | 47 -
ci/docker/Dockerfile.build.ubuntu_rat | 36 -
ci/docker/Dockerfile.publish.test.ubuntu1604_cpu | 39 -
ci/docker/Dockerfile.publish.test.ubuntu1604_gpu | 39 -
ci/docker/Dockerfile.publish.test.ubuntu1804_cpu | 41 -
ci/docker/Dockerfile.publish.test.ubuntu1804_gpu | 41 -
ci/docker/Dockerfile.publish.ubuntu1604_cpu | 44 -
ci/docker/Dockerfile.publish.ubuntu1604_gpu | 44 -
ci/docker/docker-compose.yml | 76 +-
ci/docker/install/export_gpg_keys.sh | 23 -
ci/docker/install/r.gpg | Bin 1519 -> 0 bytes
ci/docker/install/requirements | 4 +-
ci/docker/install/sbt.gpg | Bin 2210 -> 0 bytes
ci/docker/install/tensorrt.sh | 49 -
ci/docker/install/ubuntu_base.sh | 40 -
ci/docker/install/ubuntu_clang.sh | 42 -
ci/docker/install/ubuntu_clojure.sh | 30 -
ci/docker/install/ubuntu_cudnn.sh | 62 -
ci/docker/install/ubuntu_docs.sh | 36 -
ci/docker/install/ubuntu_emscripten.sh | 41 -
ci/docker/install/ubuntu_gcc8.sh | 23 -
ci/docker/install/ubuntu_julia.sh | 43 -
ci/docker/install/ubuntu_nightly_tests.sh | 35 -
ci/docker/install/ubuntu_r.sh | 50 -
ci/docker/install/ubuntu_rat.sh | 34 -
ci/docker/install/ubuntu_scala.sh | 31 -
ci/docker/runtime_functions.sh | 418 ++--
.../toolchains/aarch64-linux-gnu-toolchain.cmake | 1 +
ci/docker_cache.py | 203 --
ci/docker_cache_requirements | 24 -
ci/jenkins/Jenkins_steps.groovy | 141 +-
ci/jenkins/Jenkinsfile_centos_cpu | 1 -
ci/jenkins/Jenkinsfile_unix_cpu | 4 +-
ci/jenkins/Jenkinsfile_unix_gpu | 3 -
ci/jenkins/Jenkinsfile_website_beta | 2 +-
ci/jenkins/Jenkinsfile_website_c_docs | 48 -
ci/jenkins/Jenkinsfile_website_clojure_docs | 48 -
ci/jenkins/Jenkinsfile_website_full | 2 +-
ci/jenkins/Jenkinsfile_website_full_pr | 2 +-
ci/jenkins/Jenkinsfile_website_java_docs | 47 -
ci/jenkins/Jenkinsfile_website_julia_docs | 48 -
ci/jenkins/Jenkinsfile_website_mxnet_build | 2 +-
ci/jenkins/Jenkinsfile_website_nightly | 2 +-
ci/jenkins/Jenkinsfile_website_python_docs | 2 +-
ci/test_docker_cache.py | 272 ---
ci/windows/test_jl07_cpu.ps1 | 56 -
ci/windows/test_jl10_cpu.ps1 | 56 -
ci/windows/test_py3_cpu.ps1 | 4 +-
ci/windows/test_py3_gpu.ps1 | 4 +-
cmake/Modules/FindCUTENSOR.cmake | 33 +
cmake/Modules/FindMKL.cmake | 11 +-
cmake/libmxnet.sym | 9 +
cmake/libmxnet.ver | 13 +
config/darwin.cmake | 2 +-
config/distribution/darwin_cpu.cmake | 1 +
config/distribution/darwin_native.cmake | 34 +
config/distribution/linux_cpu.cmake | 1 +
config/distribution/linux_cu100.cmake | 1 +
config/distribution/linux_cu101.cmake | 1 +
config/distribution/linux_cu102.cmake | 1 +
config/distribution/linux_cu110.cmake | 37 +
config/linux.cmake | 2 +-
config/linux_gpu.cmake | 19 +-
conftest.py | 133 +-
contrib/tvmop/compile.py | 2 +
doap.rdf | 58 +
docs/README.md | 2 +-
docs/python_docs/README.md | 57 +-
docs/python_docs/_static/feedback.css | 37 +
docs/python_docs/_static/mxnet.css | 12 +-
docs/python_docs/_static/transformer.png | Bin 0 -> 296782 bytes
docs/python_docs/environment.yml | 38 -
docs/python_docs/python/Makefile | 23 +-
docs/python_docs/python/Makefile_sphinx | 4 +-
docs/python_docs/python/api/autograd/index.rst | 2 +-
.../python/api/{mxnet => }/context/index.rst | 0
.../python/api/contrib/autograd/index.rst | 23 -
docs/python_docs/python/api/contrib/index.rst | 14 +-
.../python/api/contrib/quantization/index.rst | 23 -
.../python/api/{mxnet => }/engine/index.rst | 0
.../python/api/{mxnet => }/executor/index.rst | 0
.../python_docs/python/api/gluon/contrib/index.rst | 95 +-
docs/python_docs/python/api/gluon/data/index.rst | 10 +-
.../python/api/gluon/data/vision/index.rst | 15 +-
docs/python_docs/python/api/gluon/hybrid_block.rst | 2 +-
docs/python_docs/python/api/gluon/index.rst | 11 +-
docs/python_docs/python/api/gluon/metric/index.rst | 23 +
docs/python_docs/python/api/gluon/nn/index.rst | 30 +-
.../python/api/gluon/parameter_dict.rst | 25 -
docs/python_docs/python/api/gluon/rnn/index.rst | 22 +-
docs/python_docs/python/api/gluon/symbol_block.rst | 3 +-
docs/python_docs/python/api/gluon/trainer.rst | 3 +-
docs/python_docs/python/api/index.rst | 140 +-
.../api/{mxnet => }/kvstore_server/index.rst | 0
.../python/api/legacy/callback/index.rst | 23 +
.../python/api/{mxnet => legacy}/image/index.rst | 0
docs/python_docs/python/api/legacy/index.rst | 72 +
.../python/api/{mxnet => legacy}/io/index.rst | 0
.../python/api/legacy/ndarray/contrib/index.rst | 23 +
.../python/api/legacy/ndarray/image/index.rst | 23 +
.../python/api/{ => legacy}/ndarray/index.rst | 0
.../python/api/legacy/ndarray/linalg/index.rst | 23 +
.../python/api/legacy/ndarray/ndarray.rst | 26 +
.../python/api/legacy/ndarray/op/index.rst | 23 +
.../python/api/legacy/ndarray/random/index.rst | 23 +
.../python/api/legacy/ndarray/register/index.rst | 23 +
.../python/api/legacy/ndarray/sparse/index.rst | 23 +
.../python/api/legacy/ndarray/utils/index.rst | 23 +
.../api/{mxnet => legacy}/recordio/index.rst | 0
.../api/{ => legacy}/symbol/contrib/index.rst | 0
.../python/api/{ => legacy}/symbol/image/index.rst | 0
.../python/api/{ => legacy}/symbol/index.rst | 0
.../api/{ => legacy}/symbol/linalg/index.rst | 0
.../python/api/{ => legacy}/symbol/op/index.rst | 0
.../api/{ => legacy}/symbol/random/index.rst | 0
.../api/{ => legacy}/symbol/register/index.rst | 0
.../api/{ => legacy}/symbol/sparse/index.rst | 0
.../python/api/{ => legacy}/symbol/symbol.rst | 0
.../api/{mxnet => legacy}/visualization/index.rst | 0
docs/python_docs/python/api/metric/index.rst | 23 -
docs/python_docs/python/api/module/index.rst | 24 -
.../python/api/mxnet/attribute/index.rst | 23 -
docs/python_docs/python/api/mxnet/base/index.rst | 23 -
.../python/api/mxnet/callback/index.rst | 23 -
.../python/api/mxnet/executor_manager/index.rst | 23 -
docs/python_docs/python/api/mxnet/index.rst | 74 -
.../python_docs/python/api/mxnet/libinfo/index.rst | 24 -
docs/python_docs/python/api/mxnet/log/index.rst | 23 -
docs/python_docs/python/api/mxnet/model/index.rst | 23 -
.../python_docs/python/api/mxnet/monitor/index.rst | 23 -
docs/python_docs/python/api/mxnet/name/index.rst | 23 -
.../python/api/mxnet/notebook/index.rst | 23 -
.../python/api/mxnet/operator/index.rst | 23 -
docs/python_docs/python/api/mxnet/random/index.rst | 23 -
.../python/api/mxnet/registry/index.rst | 23 -
.../python_docs/python/api/mxnet/runtime/index.rst | 23 -
docs/python_docs/python/api/mxnet/torch/index.rst | 23 -
.../python/api/ndarray/contrib/index.rst | 23 -
.../python_docs/python/api/ndarray/image/index.rst | 23 -
.../python/api/ndarray/linalg/index.rst | 23 -
docs/python_docs/python/api/ndarray/ndarray.rst | 26 -
docs/python_docs/python/api/ndarray/op/index.rst | 23 -
.../python/api/ndarray/random/index.rst | 23 -
.../python/api/ndarray/register/index.rst | 23 -
.../python/api/ndarray/sparse/index.rst | 23 -
.../python_docs/python/api/ndarray/utils/index.rst | 23 -
docs/python_docs/python/api/np/arrays.indexing.rst | 373 +++
docs/python_docs/python/api/np/arrays.ndarray.rst | 529 +++++
docs/python_docs/python/api/np/arrays.rst | 52 +
docs/python_docs/python/api/np/index.rst | 39 +
docs/python_docs/python/api/np/random/index.rst | 63 +
.../python/api/np/routines.array-creation.rst | 124 +
.../python/api/np/routines.array-manipulation.rst | 110 +
docs/python_docs/python/api/np/routines.io.rst | 39 +
docs/python_docs/python/api/np/routines.linalg.rst | 97 +
docs/python_docs/python/api/np/routines.math.rst | 179 ++
docs/python_docs/python/api/np/routines.rst | 42 +
docs/python_docs/python/api/np/routines.sort.rst | 57 +
.../python/api/np/routines.statistics.rst | 78 +
docs/python_docs/python/api/npx/index.rst | 101 +
.../python/api/{mxnet => }/profiler/index.rst | 0
.../python/api/{mxnet => }/rtc/index.rst | 0
docs/python_docs/python/api/runtime/index.rst | 29 +
.../python/api/{mxnet => }/test_utils/index.rst | 0
.../python/api/{mxnet => }/util/index.rst | 0
docs/python_docs/python/scripts/conf.py | 21 +-
docs/python_docs/python/scripts/md2ipynb.py | 2 +-
.../python/tutorials/deploy/export/index.rst | 19 +-
.../python/tutorials/deploy/export/onnx.md | 12 +-
docs/python_docs/python/tutorials/deploy/index.rst | 54 +-
.../inference/image_classification_jetson.md | 2 +-
.../python/tutorials/deploy/inference/index.rst | 20 +-
.../python/tutorials/deploy/inference/scala.rst | 21 -
.../tutorials/deploy/run-on-aws/use_sagemaker.rst | 19 +-
.../python/tutorials/extend/custom_layer.md | 260 ---
.../python/tutorials/extend/customop.md | 24 +-
docs/python_docs/python/tutorials/extend/index.rst | 19 +-
.../getting-started/crash-course/0-introduction.md | 78 +
.../getting-started/crash-course/1-ndarray.md | 127 --
.../getting-started/crash-course/1-nparray.md | 211 ++
.../getting-started/crash-course/2-create-nn.md | 532 +++++
.../tutorials/getting-started/crash-course/2-nn.md | 142 --
.../getting-started/crash-course/3-autograd.md | 229 +-
.../getting-started/crash-course/4-components.md | 379 ++++
.../getting-started/crash-course/4-train.md | 176 --
.../getting-started/crash-course/5-datasets.md | 310 +++
.../getting-started/crash-course/5-predict.md | 161 --
.../getting-started/crash-course/6-train-nn.md | 442 ++++
.../getting-started/crash-course/6-use_gpus.md | 146 --
.../getting-started/crash-course/7-use-gpus.md | 253 +++
.../getting-started/crash-course/index.rst | 39 +-
.../crash-course/prepare_dataset.py | 58 +
.../gluon_from_experiment_to_deployment.md | 14 +-
.../logistic_regression_explained.md | 18 +-
.../tutorials/getting-started/to-mxnet/index.rst | 8 -
docs/python_docs/python/tutorials/index.rst | 16 +-
.../gluon/blocks/activations/activations.md | 22 +-
.../packages/gluon/blocks/custom-layer.md | 267 ++-
.../gluon/blocks/custom_layer_beginners.md | 20 +-
.../tutorials/packages/gluon/blocks/hybridize.md | 12 +-
.../tutorials/packages/gluon/blocks/naming.md | 22 +-
.../packages/gluon/blocks/save_load_params.md | 20 +-
.../packages/gluon/data/data_augmentation.md | 28 +-
.../tutorials/packages/gluon/data/datasets.md | 28 +-
.../packages/gluon/image/image-augmentation.md | 148 --
.../tutorials/packages/gluon/image/index.rst | 6 -
.../tutorials/packages/gluon/image/info_gan.md | 40 +-
.../python/tutorials/packages/gluon/image/mnist.md | 24 +-
.../packages/gluon/image/pretrained_models.md | 244 --
.../python/tutorials/packages/gluon/index.rst | 28 +-
.../tutorials/packages/gluon/loss/custom-loss.md | 18 +-
.../python/tutorials/packages/gluon/loss/loss.md | 2 +-
.../tutorials/packages/gluon/text/transformer.rst | 2 +-
.../packages/gluon/training/fit_api_tutorial.md | 26 +-
.../learning_rates/learning_rate_finder.md | 16 +-
.../learning_rates/learning_rate_schedules.md | 30 +-
.../learning_rate_schedules_advanced.md | 30 +-
.../packages/gluon/training/normalization/index.md | 36 +-
.../python/tutorials/packages/index.rst | 20 +-
.../python/tutorials/packages/kvstore/kvstore.md | 16 +-
.../python/tutorials/packages/legacy/index.rst | 41 +
.../packages/legacy/ndarray/01-ndarray-intro.md | 172 ++
.../legacy/ndarray/02-ndarray-operations.md | 257 +++
.../{ => legacy}/ndarray/03-ndarray-contexts.md | 0
.../legacy/ndarray/gotchas_numpy_in_mxnet.md | 189 ++
.../tutorials/packages/legacy/ndarray/index.rst | 61 +
.../packages/legacy/ndarray/sparse/csr.md | 562 +++++
.../packages/{ => legacy}/ndarray/sparse/index.rst | 0
.../packages/legacy/ndarray/sparse/row_sparse.md | 584 +++++
.../packages/legacy/ndarray/sparse/train_gluon.md | 476 ++++
.../tutorials/packages/ndarray/01-ndarray-intro.md | 172 --
.../packages/ndarray/02-ndarray-operations.md | 257 ---
.../packages/ndarray/gotchas_numpy_in_mxnet.md | 187 --
.../python/tutorials/packages/ndarray/index.rst | 54 -
.../tutorials/packages/ndarray/sparse/csr.md | 562 -----
.../packages/ndarray/sparse/row_sparse.md | 584 -----
.../packages/ndarray/sparse/train_gluon.md | 476 ----
.../python/tutorials/packages/np/cheat-sheet.md | 463 ++++
.../python/tutorials/packages/np/index.rst | 32 +
.../python/tutorials/packages/np/np-vs-numpy.md | 113 +
.../tutorials/packages/onnx/fine_tuning_gluon.md | 62 +-
.../packages/onnx/inference_on_onnx_model.md | 40 +-
.../python/tutorials/packages/optimizer/index.md | 30 +-
.../python/tutorials/packages/viz/index.rst | 4 +-
.../python/tutorials/performance/backend/amp.md | 24 +-
.../python/tutorials/performance/backend/index.rst | 9 +-
.../performance/backend/mkldnn/mkldnn_readme.md | 6 +-
.../tutorials/performance/backend/profiler.md | 22 +-
.../performance/backend/tensorrt/index.rst | 35 -
.../backend/tensorrt/wavenet_optimized.svg | 1 -
.../backend/tensorrt/wavenet_unoptimized.svg | 17 -
.../python/tutorials/performance/index.rst | 11 +-
docs/python_docs/requirements | 30 +
.../themes/mx-theme/mxtheme/feedback.html | 10 +
.../themes/mx-theme/mxtheme/footer.html | 12 +-
.../themes/mx-theme/mxtheme/header_top.html | 5 +-
.../themes/mx-theme/mxtheme/layout.html | 12 +-
.../mxtheme/static/sphinx_materialdesign_theme.css | 2 +-
.../static/sphinx_materialdesign_theme.css.map | 2 +-
.../mxtheme/static/sphinx_materialdesign_theme.js | 454 ++--
.../static/sphinx_materialdesign_theme.js.map | 2 +-
.../python_docs/themes/mx-theme/src/js/feedback.js | 33 +
.../themes/mx-theme/src/js/scrollspy.js | 25 +-
.../mx-theme/src/js/sphinx_materialdesign_theme.js | 20 +-
.../themes/mx-theme/src/scss/_root.scss | 22 +
.../themes/mx-theme/src/scss/footer/_footer.scss | 4 +
.../themes/mx-theme/src/scss/grid/_simplegrid.scss | 9 -
.../themes/mx-theme/src/scss/layout/_layout.scss | 13 +-
docs/static_site/Makefile | 5 +-
docs/static_site/src/.htaccess | 18 +-
docs/static_site/src/_config.yml | 6 +-
docs/static_site/src/_config_beta.yml | 8 +-
docs/static_site/src/_config_prod.yml | 8 +-
docs/static_site/src/_includes/callout.html | 1 +
docs/static_site/src/_includes/feedback.html | 10 +
docs/static_site/src/_includes/footer.html | 10 +-
.../src/_includes/get_started/get_started.html | 128 +-
.../_includes/get_started/linux/python/cpu/pip.md | 60 +-
.../_includes/get_started/linux/python/gpu/pip.md | 9 +-
.../src/_includes/get_started/pip_snippet.md | 2 +-
docs/static_site/src/_includes/head.html | 3 +
docs/static_site/src/_includes/important.html | 1 +
docs/static_site/src/_includes/note.html | 1 +
docs/static_site/src/_includes/tip.html | 1 +
docs/static_site/src/_includes/warning.html | 1 +
docs/static_site/src/_layouts/page_api.html | 3 +
docs/static_site/src/_sass/feedback.scss | 39 +
docs/static_site/src/_sass/minima/_docs.scss | 10 +
.../src/_sass/minima/_getting_started.scss | 2 +
docs/static_site/src/_sass/minima/_layout.scss | 12 +-
docs/static_site/src/assets/img/autogluon.png | Bin 0 -> 11687 bytes
docs/static_site/src/assets/img/tune.png | Bin 0 -> 24342 bytes
docs/static_site/src/assets/js/copycode.js | 2 +-
docs/static_site/src/assets/js/feedback.js | 33 +
docs/static_site/src/assets/main.scss | 1 +
docs/static_site/src/pages/api/api.html | 72 +-
.../cpp/docs/tutorials/multi_threaded_inference.md | 20 +-
docs/static_site/src/pages/api/cpp/index.md | 8 +-
.../src/pages/api/developer_guide/profiling.md | 18 +-
.../src/pages/api/faq/add_op_in_backend.md | 1 +
docs/static_site/src/pages/api/faq/caffe.md | 148 --
docs/static_site/src/pages/api/faq/cloud.md | 106 +-
docs/static_site/src/pages/api/faq/env_var.md | 78 +-
docs/static_site/src/pages/api/faq/nnpack.md | 162 --
docs/static_site/src/pages/api/faq/perf.md | 2 +-
.../src/pages/api/faq/s3_integration.md | 5 +-
docs/static_site/src/pages/api/faq/using_rtc.md | 465 ++++
docs/static_site/src/pages/community/code_guide.md | 100 +
.../static_site/src/pages/community/code_review.md | 166 ++
.../src/pages/community/committer_guide.md | 111 +
docs/static_site/src/pages/community/community.md | 115 +
docs/static_site/src/pages/community/contribute.md | 192 --
docs/static_site/src/pages/community/document.md | 125 +
.../src/pages/community/error_handling.md | 114 +
docs/static_site/src/pages/community/git_howto.md | 164 ++
docs/static_site/src/pages/community/index.md | 129 ++
.../src/pages/community/pull_request.md | 105 +
docs/static_site/src/pages/ecosystem.html | 53 +-
.../src/pages/get_started/build_from_source.md | 8 +-
docs/static_site/src/pages/get_started/download.md | 3 +-
.../autoencoder/convolutional_autoencoder.ipynb | 61 +-
.../amp_model_conversion.py | 2 +-
example/extensions/lib_api/Makefile | 2 +-
example/extensions/lib_api/init_lib.cc | 6 +-
example/extensions/lib_custom_op/Makefile | 11 +-
example/extensions/lib_custom_op/gemm_lib.cc | 30 +-
example/extensions/lib_custom_op/relu_lib.cc | 177 ++
example/extensions/lib_custom_op/relu_lib.cu | 173 +-
example/extensions/lib_custom_op/relu_lib.h | 90 +
example/extensions/lib_custom_op/test_gemm.py | 79 +-
example/extensions/lib_custom_op/test_relu.py | 46 +-
.../extensions/lib_custom_op/test_transposecsr.py | 24 +-
.../lib_custom_op/test_transposerowsp.py | 21 +-
.../extensions/lib_custom_op/transposecsr_lib.cc | 36 +-
.../extensions/lib_custom_op/transposerowsp_lib.cc | 38 +-
example/extensions/lib_pass/Makefile | 2 +-
example/extensions/lib_pass/README.md | 103 +-
example/extensions/lib_pass/example_connection.png | Bin 0 -> 8443 bytes
example/extensions/lib_pass/pass_lib.cc | 68 +-
example/extensions/lib_pass/test_pass.py | 26 +-
example/extensions/lib_subgraph/Makefile | 2 +-
example/extensions/lib_subgraph/README.md | 165 +-
example/extensions/lib_subgraph/subgraph_lib.cc | 239 +-
example/extensions/lib_subgraph/test_subgraph.py | 68 +-
example/gluon/image_classification.py | 3 +-
example/gluon/mnist/README.md | 7 +-
example/gluon/mnist/mnist.py | 7 +-
.../multi_threaded_inference.cc | 10 +-
example/probability/VAE/VAE.md | 259 +++
example/probability/VAE/VAE_11_0.png | Bin 0 -> 9062 bytes
example/probability/VAE/VAE_14_0.png | Bin 0 -> 15863 bytes
example/profiler/profiler_matmul.py | 4 +-
include/mxnet/base.h | 2 +-
include/mxnet/c_api.h | 422 ++--
include/mxnet/c_api_error.h | 4 +
include/mxnet/c_api_test.h | 16 +
include/mxnet/lib_api.h | 1416 +++---------
include/mxnet/libinfo.h | 16 +-
include/mxnet/ndarray.h | 47 +-
include/mxnet/resource.h | 3 +-
include/mxnet/rtc.h | 4 +-
make/config.mk | 248 --
make/config/libmxnet.sym | 10 -
make/config/libmxnet.ver | 14 -
make/config_jetson.mk | 219 --
make/osx.mk | 153 --
make/readthedocs.mk | 92 -
make/staticbuild/darwin_cpu.mk | 167 --
make/staticbuild/darwin_mkl.mk | 167 --
make/staticbuild/linux_cpu.mk | 167 --
make/staticbuild/linux_cu100.mk | 180 --
make/staticbuild/linux_cu101.mk | 181 --
make/staticbuild/linux_cu102.mk | 181 --
make/staticbuild/linux_cu92.mk | 180 --
make/staticbuild/linux_native.mk | 167 --
mkldnn.mk | 65 -
plugin/caffe/README.md | 58 -
plugin/caffe/caffe.mk | 32 -
plugin/caffe/caffe_blob.cc | 94 -
plugin/caffe/caffe_blob.h | 117 -
plugin/caffe/caffe_common.cc | 48 -
plugin/caffe/caffe_common.h | 97 -
plugin/caffe/caffe_data_iter.cc | 273 ---
plugin/caffe/caffe_fieldentry.h | 113 -
plugin/caffe/caffe_loss-inl.h | 303 ---
plugin/caffe/caffe_loss.cc | 73 -
plugin/caffe/caffe_loss.cu | 53 -
plugin/caffe/caffe_op-inl.h | 348 ---
plugin/caffe/caffe_op.cc | 74 -
plugin/caffe/caffe_op.cu | 53 -
plugin/caffe/caffe_stream.cc | 37 -
plugin/caffe/caffe_stream.h | 38 -
python/mxnet/__init__.py | 6 +-
python/mxnet/_ctypes/ndarray.py | 11 +-
python/mxnet/{contrib => }/amp/__init__.py | 0
python/mxnet/amp/amp.py | 827 +++++++
python/mxnet/{contrib => }/amp/lists/__init__.py | 0
python/mxnet/amp/lists/symbol_bf16.py | 622 +++++
python/mxnet/amp/lists/symbol_fp16.py | 716 ++++++
python/mxnet/amp/loss_scaler.py | 74 +
python/mxnet/attribute.py | 46 +-
python/mxnet/autograd.py | 14 +-
python/mxnet/base.py | 71 +-
python/mxnet/context.py | 49 +-
python/mxnet/contrib/__init__.py | 1 -
python/mxnet/contrib/amp/amp.py | 788 -------
python/mxnet/contrib/amp/lists/symbol_bf16.py | 622 -----
python/mxnet/contrib/amp/lists/symbol_fp16.py | 621 -----
python/mxnet/contrib/amp/loss_scaler.py | 77 -
python/mxnet/contrib/autograd.py | 228 --
.../mxnet/contrib/onnx/mx2onnx/_op_translations.py | 41 +-
.../mxnet/contrib/onnx/onnx2mx/_op_translations.py | 27 +-
python/mxnet/cython/base.pyi | 39 +-
python/mxnet/cython/ndarray.pyx | 9 +-
python/mxnet/dlpack.py | 185 ++
python/mxnet/error.py | 4 +
python/mxnet/gluon/__init__.py | 2 +
python/mxnet/gluon/block.py | 362 +--
python/mxnet/gluon/contrib/__init__.py | 6 -
python/mxnet/gluon/contrib/cnn/__init__.py | 25 -
python/mxnet/gluon/contrib/cnn/conv_layers.py | 399 ----
python/mxnet/gluon/contrib/data/__init__.py | 3 -
python/mxnet/gluon/contrib/data/sampler.py | 62 -
python/mxnet/gluon/contrib/data/text.py | 176 --
python/mxnet/gluon/contrib/estimator/estimator.py | 2 +-
python/mxnet/gluon/contrib/nn/__init__.py | 26 -
python/mxnet/gluon/contrib/nn/basic_layers.py | 371 ---
python/mxnet/gluon/contrib/rnn/__init__.py | 28 -
python/mxnet/gluon/contrib/rnn/conv_rnn_cell.py | 918 --------
python/mxnet/gluon/contrib/rnn/rnn_cell.py | 431 ----
python/mxnet/gluon/data/dataloader.py | 31 +-
python/mxnet/gluon/data/sampler.py | 43 +-
python/mxnet/gluon/loss.py | 276 ++-
python/mxnet/gluon/metric.py | 116 +-
python/mxnet/gluon/model_zoo/vision/densenet.py | 5 +-
python/mxnet/gluon/model_zoo/vision/inception.py | 15 +-
python/mxnet/gluon/model_zoo/vision/squeezenet.py | 3 +-
python/mxnet/gluon/nn/basic_layers.py | 186 +-
python/mxnet/gluon/nn/conv_layers.py | 597 ++++-
python/mxnet/gluon/parameter.py | 29 +-
python/mxnet/gluon/probability/__init__.py | 26 +
python/mxnet/gluon/probability/block/__init__.py | 22 +
.../gluon/probability/block/stochastic_block.py | 134 ++
.../gluon/probability/distributions/__init__.py | 86 +
.../gluon/probability/distributions/bernoulli.py | 139 ++
.../mxnet/gluon/probability/distributions/beta.py | 97 +
.../gluon/probability/distributions/binomial.py | 145 ++
.../gluon/probability/distributions/categorical.py | 168 ++
.../gluon/probability/distributions/cauchy.py | 96 +
.../mxnet/gluon/probability/distributions/chi2.py | 48 +
.../gluon/probability/distributions/constraint.py | 548 +++++
.../gluon/probability/distributions/dirichlet.py | 102 +
.../probability/distributions/distribution.py | 198 ++
.../gluon/probability/distributions/divergence.py | 382 ++++
.../gluon/probability/distributions/exp_family.py | 68 +
.../gluon/probability/distributions/exponential.py | 110 +
.../probability/distributions/fishersnedecor.py | 107 +
.../mxnet/gluon/probability/distributions/gamma.py | 102 +
.../gluon/probability/distributions/geometric.py | 133 ++
.../gluon/probability/distributions/gumbel.py | 109 +
.../gluon/probability/distributions/half_cauchy.py | 81 +
.../gluon/probability/distributions/half_normal.py | 82 +
.../gluon/probability/distributions/independent.py | 94 +
.../gluon/probability/distributions/laplace.py | 143 ++
.../gluon/probability/distributions/multinomial.py | 125 +
.../distributions/multivariate_normal.py | 174 ++
.../probability/distributions/negative_binomial.py | 140 ++
.../gluon/probability/distributions/normal.py | 166 ++
.../distributions/one_hot_categorical.py | 105 +
.../gluon/probability/distributions/pareto.py | 83 +
.../gluon/probability/distributions/poisson.py | 110 +
.../probability/distributions/relaxed_bernoulli.py | 138 ++
.../distributions/relaxed_one_hot_categorical.py | 177 ++
.../gluon/probability/distributions/studentT.py | 119 +
.../distributions/transformed_distribution.py | 105 +
.../gluon/probability/distributions/uniform.py | 101 +
.../mxnet/gluon/probability/distributions/utils.py | 217 ++
.../gluon/probability/distributions/weibull.py | 85 +
.../gluon/probability/transformation/__init__.py | 23 +
.../gluon/probability/transformation/domain_map.py | 123 +
.../probability/transformation/transformation.py | 305 +++
python/mxnet/gluon/rnn/__init__.py | 2 +-
python/mxnet/gluon/rnn/conv_rnn_cell.py | 918 ++++++++
python/mxnet/gluon/rnn/rnn_cell.py | 408 +++-
python/mxnet/gluon/trainer.py | 30 +-
python/mxnet/initializer.py | 8 +-
python/mxnet/io/io.py | 4 +-
python/mxnet/library.py | 38 +-
python/mxnet/name.py | 53 +-
python/mxnet/ndarray/contrib.py | 4 +-
python/mxnet/ndarray/ndarray.py | 298 +--
python/mxnet/ndarray/numpy/_op.py | 220 +-
python/mxnet/ndarray/numpy/random.py | 16 +-
python/mxnet/ndarray/numpy_extension/random.py | 2 +-
python/mxnet/numpy/fallback.py | 122 +-
python/mxnet/numpy/linalg.py | 174 +-
python/mxnet/numpy/multiarray.py | 1647 ++++++++------
python/mxnet/numpy/random.py | 6 +-
python/mxnet/numpy_extension/utils.py | 92 +-
python/mxnet/operator.py | 26 +
python/mxnet/optimizer/lars.py | 16 +-
python/mxnet/optimizer/updater.py | 4 +-
python/mxnet/profiler.py | 72 +-
python/mxnet/random.py | 28 +-
python/mxnet/runtime.py | 5 +-
python/mxnet/symbol/contrib.py | 4 +-
python/mxnet/symbol/numpy/_symbol.py | 241 +-
python/mxnet/symbol/numpy/random.py | 2 +-
python/mxnet/symbol/register.py | 28 +-
python/mxnet/symbol/symbol.py | 217 +-
python/mxnet/test_utils.py | 595 +++--
python/mxnet/torch.py | 182 --
python/mxnet/util.py | 70 +-
python/setup.py | 10 +-
setup-utils/install-mxnet-amz-linux.sh | 82 -
setup-utils/install-mxnet-fedora-python.sh | 55 -
setup-utils/install-mxnet-osx-python.sh | 554 -----
setup-utils/install-mxnet-ubuntu-python.sh | 59 -
setup-utils/install-mxnet-ubuntu-r.sh | 67 -
setup-utils/install-mxnet-virtualenv.sh | 123 -
setup-utils/install-mxnet-windows-python.bat | 295 ---
src/api/operator/numpy/linalg/np_norm.cc | 2 +-
.../numpy/np_broadcast_reduce_op_boolean.cc | 4 +-
.../operator/numpy/np_broadcast_reduce_op_index.cc | 4 +-
.../operator/numpy/np_broadcast_reduce_op_value.cc | 16 +-
src/api/operator/numpy/np_cumsum.cc | 2 +-
src/api/operator/numpy/np_delete_op.cc | 3 +-
src/api/operator/numpy/np_dot_op.cc | 50 +
src/api/operator/numpy/np_ediff1d_op.cc | 2 +-
src/api/operator/numpy/np_einsum_op.cc | 2 +-
.../operator/numpy/np_elemwise_unary_op_basic.cc | 15 +-
src/api/operator/numpy/np_fill_diagonal_op.cc | 2 +-
src/api/operator/numpy/np_histogram_op.cc | 2 +-
src/api/operator/numpy/np_init_op.cc | 30 +-
src/api/operator/numpy/np_insert_op.cc | 9 +-
src/api/operator/numpy/np_interp_op.cc | 4 +-
src/api/operator/numpy/np_matrix_op.cc | 114 +-
src/api/operator/numpy/np_moments_op.cc | 6 +-
src/api/operator/numpy/np_nan_to_num_op.cc | 2 +-
src/api/operator/numpy/np_ordering_op.cc | 88 +
src/api/operator/numpy/np_pad_op.cc | 2 +-
src/api/operator/numpy/np_percentile_op.cc | 4 +-
src/api/operator/numpy/np_repeat_op.cc | 2 +-
src/api/operator/numpy/np_tensordot_op.cc | 2 +-
src/api/operator/numpy/np_unique_op.cc | 2 +-
src/api/operator/numpy/np_window_op.cc | 2 +-
src/api/operator/numpy/random/np_choice_op.cc | 2 +-
src/api/operator/numpy/random/np_exponential_op.cc | 6 +-
src/api/operator/numpy/random/np_laplace_op.cc | 6 +-
.../operator/numpy/random/np_location_scale_op.cc | 14 +-
src/api/operator/numpy/random/np_multinomial_op.cc | 75 +
src/api/operator/numpy/random/np_pareto_op.cc | 6 +-
src/api/operator/numpy/random/np_power_op.cc | 6 +-
src/api/operator/numpy/random/np_rayleigh_op.cc | 6 +-
src/api/operator/numpy/random/np_weibull_op.cc | 6 +-
src/api/operator/random/np_gamma_op.cc | 8 +-
src/api/operator/random/np_normal_op.cc | 8 +-
src/api/operator/random/np_uniform_op.cc | 9 +-
src/api/operator/tensor/matrix_op.cc | 2 +-
src/api/operator/ufunc_helper.cc | 8 +-
src/c_api/c_api.cc | 927 +++++---
src/c_api/c_api_common.h | 4 +-
src/c_api/c_api_error.cc | 206 --
src/c_api/c_api_ndarray.cc | 75 +-
src/c_api/c_api_profile.cc | 45 +-
src/c_api/c_api_symbolic.cc | 474 ++--
src/c_api/c_api_test.cc | 22 +
src/common/cuda/rtc.cc | 244 ++
src/common/cuda/rtc.h | 92 +
src/common/cuda/rtc/backward_functions-inl.h | 480 ++++
src/common/cuda/rtc/forward_functions-inl.h | 923 ++++++++
src/common/cuda/rtc/half-inl.h | 84 +
src/common/cuda/rtc/reducer-inl.h | 109 +
src/common/cuda/rtc/special_functions-inl.h | 300 +++
src/common/cuda/rtc/util-inl.h | 389 ++++
src/common/cuda/rtc/vectorization-inl.h | 463 ++++
src/common/cuda/utils.cc | 90 +
src/common/cuda/utils.h | 874 +++++++
src/common/cuda_utils.cc | 90 -
src/common/cuda_utils.h | 809 -------
src/common/exec_utils.h | 99 +-
src/common/rtc.cc | 6 +-
src/common/utils.cc | 25 +
src/common/utils.h | 36 +
src/engine/naive_engine.cc | 35 +-
src/engine/stream_manager.h | 2 +-
src/engine/threaded_engine.cc | 2 +-
src/engine/threaded_engine_perdevice.cc | 32 +-
src/engine/threaded_engine_pooled.cc | 15 +-
src/imperative/attach_op_execs_pass.cc | 84 +-
src/imperative/cached_op.cc | 67 +-
src/imperative/cached_op.h | 9 +-
src/imperative/cached_op_threadsafe.cc | 2 +-
src/imperative/eliminate_common_expr_pass.cc | 9 +-
src/imperative/exec_pass.h | 16 +-
src/imperative/imperative.cc | 40 +-
src/imperative/imperative_utils.cc | 11 +-
src/imperative/imperative_utils.h | 355 ++-
src/imperative/pointwise_fusion_pass.cc | 523 +++--
src/imperative/simple_partition_pass.cc | 265 +++
src/imperative/simple_partition_pass.h | 599 ++---
src/initialize.cc | 205 +-
src/io/batchify.cc | 16 +-
src/io/dataloader.cc | 16 +-
src/io/dataset.cc | 48 +-
src/io/image_aug_default.cc | 2 +-
src/io/image_det_aug_default.cc | 2 +-
src/io/iter_csv.cc | 30 +-
src/io/iter_image_det_recordio.cc | 19 +-
src/io/iter_image_recordio.cc | 19 +-
src/io/iter_image_recordio_2.cc | 46 +-
src/io/iter_libsvm.cc | 16 +-
src/io/iter_mnist.cc | 22 +-
src/io/iter_sampler.cc | 23 +-
src/kvstore/kvstore.cc | 3 +-
src/kvstore/kvstore_nccl.h | 2 +-
src/lib_api.cc | 1622 +++++++++++++
src/libinfo.cc | 7 +-
src/ndarray/ndarray.cc | 166 +-
src/ndarray/ndarray_function.cu | 2 +-
src/nnvm/gradient.cc | 9 +-
src/nnvm/graph_editor.cc | 4 +-
src/nnvm/low_precision_pass.cc | 15 +-
src/nnvm/tvm_bridge.cc | 4 +-
src/operator/all_finite-inl.h | 100 +
src/operator/all_finite.cc | 170 ++
src/operator/{contrib => }/all_finite.cu | 0
src/operator/{contrib => }/amp_graph_pass.cc | 0
src/operator/bilinear_sampler.cc | 14 +-
src/operator/bilinear_sampler.cu | 2 +-
src/operator/contrib/all_finite-inl.h | 100 -
src/operator/contrib/all_finite.cc | 168 --
src/operator/contrib/bilinear_resize-inl.h | 4 +-
src/operator/contrib/boolean_mask.cc | 4 +-
src/operator/contrib/bounding_box-inl.h | 11 +
src/operator/contrib/bounding_box.cc | 33 +-
src/operator/contrib/deformable_convolution-inl.h | 511 -----
src/operator/contrib/deformable_convolution.cc | 108 -
src/operator/contrib/deformable_psroi_pooling.cu | 2 +-
src/operator/contrib/dgl_graph.cc | 49 +-
src/operator/contrib/dynamic_shape_ops-inl.h | 92 +
src/operator/contrib/dynamic_shape_ops.cc | 144 ++
src/operator/contrib/gradient_multiplier_op.cu | 4 +-
.../contrib/intgemm/intgemm_fully_connected_op.cc | 328 +++
src/operator/contrib/intgemm/max_absolute_op.cc | 119 +
src/operator/contrib/intgemm/prepare_data_op.cc | 134 ++
src/operator/contrib/intgemm/prepare_weight_op.cc | 180 ++
src/operator/contrib/intgemm/take_weight_op.cc | 146 ++
.../contrib/modulated_deformable_convolution-inl.h | 576 -----
.../contrib/modulated_deformable_convolution.cc | 111 -
src/operator/contrib/multi_proposal.cc | 8 +-
src/operator/contrib/nn/deformable_im2col.cuh | 2 +-
.../contrib/nn/modulated_deformable_im2col.cuh | 2 +-
src/operator/contrib/proposal.cc | 8 +-
src/operator/contrib/psroi_pooling.cu | 2 +-
src/operator/contrib/rroi_align.cc | 2 +-
src/operator/contrib/stes_op.cu | 8 +-
src/operator/contrib/transformer-inl.h | 222 ++
src/operator/contrib/transformer.cc | 191 ++
src/operator/contrib/transformer.cu | 18 +-
src/operator/control_flow.cc | 12 +-
src/operator/convolution_v1-inl.h | 556 -----
src/operator/convolution_v1.cc | 68 -
src/operator/convolution_v1.cu | 49 -
src/operator/correlation-inl.h | 4 +-
src/operator/custom/custom.cc | 73 +-
src/operator/custom/ndarray_op.cc | 2 +
src/operator/deformable_convolution-inl.h | 511 +++++
src/operator/deformable_convolution.cc | 108 +
.../{contrib => }/deformable_convolution.cu | 0
src/operator/fusion/fused_op-inl.h | 872 +------
src/operator/fusion/fused_op.cc | 4 +-
src/operator/fusion/fused_op.cu | 199 +-
src/operator/fusion/fused_op.h | 5 +-
src/operator/image/crop.cc | 58 +-
src/operator/image/image_random-inl.h | 4 +-
src/operator/image/image_random.cc | 189 +-
src/operator/image/resize.cc | 57 +-
src/operator/instance_norm-inl.h | 364 ++-
src/operator/instance_norm.cc | 87 +-
src/operator/instance_norm.cu | 10 +-
src/operator/leaky_relu-inl.h | 20 +
src/operator/leaky_relu.cc | 4 +-
src/operator/linalg.h | 8 +
src/operator/linalg_impl.h | 36 +-
.../modulated_deformable_convolution-inl.h | 576 +++++
src/operator/modulated_deformable_convolution.cc | 111 +
.../modulated_deformable_convolution.cu | 0
src/operator/mshadow_op.h | 295 ++-
src/operator/mxnet_op.h | 2 +-
src/operator/nn/batch_norm.cc | 14 +-
src/operator/nn/batch_norm.cu | 570 ++++-
src/operator/nn/concat.cc | 1 +
src/operator/nn/convolution-inl.h | 4 +-
src/operator/nn/convolution.cc | 3 -
src/operator/nn/ctc_loss-inl.h | 5 +-
src/operator/nn/ctc_loss.cc | 1 +
src/operator/nn/ctc_loss.cu | 1 +
src/operator/nn/cudnn/cudnn_activation-inl.h | 2 +-
src/operator/nn/cudnn/cudnn_algoreg-inl.h | 2 +-
src/operator/nn/cudnn/cudnn_batch_norm-inl.h | 26 +-
src/operator/nn/cudnn/cudnn_convolution-inl.h | 29 +-
src/operator/nn/cudnn/cudnn_deconvolution-inl.h | 29 +-
src/operator/nn/deconvolution-inl.h | 4 +-
src/operator/nn/depthwise_convolution-inl.h | 2 +-
src/operator/nn/depthwise_convolution_tf.cuh | 2 +-
src/operator/nn/dropout-inl.h | 5 +-
src/operator/nn/fully_connected.cc | 3 -
src/operator/nn/group_norm-inl.h | 93 +-
src/operator/nn/layer_norm-inl.h | 91 +-
src/operator/nn/layer_norm.cu | 4 +-
src/operator/nn/log_softmax.cc | 1 +
src/operator/nn/mkldnn/mkldnn_act-inl.h | 7 -
src/operator/nn/mkldnn/mkldnn_act.cc | 2 +-
src/operator/nn/mkldnn/mkldnn_base-inl.h | 21 -
src/operator/nn/mkldnn/mkldnn_batch_norm-inl.h | 60 +-
src/operator/nn/moments-inl.h | 12 +-
src/operator/nn/pool.cuh | 2 +-
src/operator/nn/pooling.cc | 8 +-
src/operator/nn/softmax-inl.h | 12 +-
src/operator/nn/softmax.cc | 1 +
src/operator/nn/upsampling-inl.h | 4 +-
src/operator/nn/upsampling.cc | 1 +
src/operator/nnpack/nnpack_convolution-inl.h | 124 -
src/operator/nnpack/nnpack_fully_connected-inl.h | 108 -
src/operator/nnpack/nnpack_pooling-inl.h | 91 -
src/operator/nnpack/nnpack_util.cc | 37 -
src/operator/nnpack/nnpack_util.h | 64 -
.../linalg/broadcast_reduce_customized-inl.cuh | 21 +-
.../numpy/linalg/broadcast_reduce_customized-inl.h | 4 +
.../numpy/linalg/broadcast_reduce_op_customized.h | 4 +-
src/operator/numpy/linalg/np_matrix_rank-inl.h | 16 +-
src/operator/numpy/linalg/np_norm-inl.h | 4 +-
src/operator/numpy/linalg/np_pinv-inl.h | 30 +-
src/operator/numpy/linalg/np_qr-inl.h | 186 +-
src/operator/numpy/np_broadcast_reduce_op.cuh | 44 +
src/operator/numpy/np_broadcast_reduce_op.h | 123 +-
src/operator/numpy/np_broadcast_reduce_op_index.cc | 12 +-
src/operator/numpy/np_broadcast_reduce_op_index.cu | 4 +-
src/operator/numpy/np_cross-inl.h | 58 +-
src/operator/numpy/np_cumsum-inl.h | 12 +-
src/operator/numpy/np_diff-inl.h | 24 +-
src/operator/numpy/np_dot.cc | 6 +-
src/operator/numpy/np_dot.cu | 4 +-
src/operator/numpy/np_ediff1d_op-inl.h | 2 +-
src/operator/numpy/np_einsum_op-inl.h | 4 +
src/operator/numpy/np_einsum_op.cc | 5 +-
src/operator/numpy/np_einsum_op.cu | 867 ++++++-
src/operator/numpy/np_einsum_path_op-inl.h | 91 +-
.../numpy/np_elemwise_broadcast_logic_op.cc | 87 +-
.../numpy/np_elemwise_broadcast_logic_op.cu | 4 +-
src/operator/numpy/np_elemwise_broadcast_op.cu | 56 +-
src/operator/numpy/np_elemwise_broadcast_op.h | 10 +-
.../numpy/np_elemwise_broadcast_op_extended.cc | 6 +-
.../numpy/np_elemwise_broadcast_op_extended.cu | 67 +-
.../numpy/np_elemwise_broadcast_op_extended_sec.cu | 33 +-
src/operator/numpy/np_elemwise_unary_op_basic.cc | 7 +-
src/operator/numpy/np_elemwise_unary_op_basic.cu | 173 +-
src/operator/numpy/np_fill_diagonal_op-inl.h | 2 +-
src/operator/numpy/np_indexing_op.cc | 551 +++++
src/operator/numpy/np_indexing_op.cu | 452 ++++
src/operator/numpy/np_indexing_op.h | 130 ++
src/operator/numpy/np_init_op.cc | 1 +
src/operator/numpy/np_init_op.h | 4 +-
src/operator/numpy/np_interp_op-inl.h | 28 +-
src/operator/numpy/np_kron-inl.h | 4 +-
src/operator/numpy/np_matrix_op-inl.h | 112 +-
src/operator/numpy/np_matrix_op.cc | 28 +-
src/operator/numpy/np_matrix_op.cu | 2 +-
src/operator/numpy/np_nonzero_op-inl.h | 19 +
src/operator/numpy/np_nonzero_op.cc | 7 +-
src/operator/numpy/np_nonzero_op.cu | 2 +-
src/operator/numpy/np_pad_op-inl.h | 191 +-
src/operator/numpy/np_polynomial_op-inl.h | 2 +-
src/operator/numpy/np_polynomial_op.cc | 6 +-
src/operator/numpy/np_polynomial_op.cu | 2 +-
src/operator/numpy/np_tensordot_op-inl.h | 31 +-
src/operator/numpy/np_true_divide-inl.h | 14 +-
src/operator/numpy/np_true_divide.cu | 3 +-
src/operator/numpy/np_where_op-inl.h | 12 +-
src/operator/numpy/random/dist_common.h | 21 +-
src/operator/numpy/random/np_bernoulli_op.h | 4 +-
src/operator/numpy/random/np_exponential_op.h | 6 +-
src/operator/numpy/random/np_gamma_op.cc | 31 +-
src/operator/numpy/random/np_gamma_op.cu | 3 +
src/operator/numpy/random/np_gamma_op.h | 86 +-
src/operator/numpy/random/np_laplace_op.h | 4 +-
src/operator/numpy/random/np_location_scale_op.h | 14 +-
src/operator/numpy/random/np_multinomial_op.h | 16 +-
src/operator/numpy/random/np_normal_op.h | 14 +-
src/operator/numpy/random/np_pareto_op.h | 6 +-
src/operator/numpy/random/np_power_op.h | 4 +-
src/operator/numpy/random/np_rayleigh_op.h | 6 +-
src/operator/numpy/random/np_uniform_op.h | 4 +-
src/operator/numpy/random/np_weibull_op.h | 6 +-
src/operator/operator_common.h | 2 +-
src/operator/operator_tune.cc | 4 +-
src/operator/optimizer_op.cc | 2 +
src/operator/pad.cu | 2 +-
src/operator/pooling_v1-inl.h | 378 ---
src/operator/pooling_v1.cc | 109 -
src/operator/pooling_v1.cu | 55 -
.../quantization/mkldnn/mkldnn_quantized_act.cc | 2 +-
src/operator/quantization/quantization_utils.h | 2 +-
src/operator/quantization/quantize_graph_pass.cc | 7 +-
src/operator/quantization/quantized_concat.cc | 1 +
.../quantization/quantized_elemwise_mul.cc | 4 +-
.../quantization/quantized_fully_connected.cc | 2 +-
src/operator/random/multisample_op.cc | 17 +-
src/operator/random/multisample_op.h | 6 +-
src/operator/random/pdf_op.h | 4 +-
src/operator/random/sample_op.cc | 1 +
src/operator/rnn-inl.h | 5 +-
src/operator/rnn.cc | 4 +
src/operator/roi_pooling-inl.h | 5 +
src/operator/subgraph/build_subgraph.cc | 91 +-
src/operator/subgraph/default_subgraph_property.cc | 16 +-
.../subgraph/default_subgraph_property_v2.cc | 4 +-
.../partitioner/custom_subgraph_property.h | 89 +-
src/operator/subgraph/subgraph_property.h | 29 +-
src/operator/subgraph/tensorrt/onnx_to_tensorrt.cc | 8 +-
src/operator/subgraph/tensorrt/tensorrt-inl.h | 48 +-
src/operator/subgraph/tensorrt/tensorrt.cu | 6 +-
src/operator/tensor/amp_cast.cc | 4 +
src/operator/tensor/broadcast_reduce-inl.cuh | 366 +--
src/operator/tensor/broadcast_reduce-inl.h | 592 ++++-
src/operator/tensor/broadcast_reduce_norm_value.cc | 1 +
src/operator/tensor/broadcast_reduce_op.h | 22 +-
src/operator/tensor/cast_storage-inl.h | 2 +-
src/operator/tensor/dot-inl.cuh | 26 +-
.../tensor/elemwise_binary_broadcast_op-inl.cuh | 82 -
.../tensor/elemwise_binary_broadcast_op.cc | 452 ++++
src/operator/tensor/elemwise_binary_broadcast_op.h | 233 +-
.../tensor/elemwise_binary_broadcast_op_basic.cu | 27 +-
.../elemwise_binary_broadcast_op_extended.cu | 21 +-
.../tensor/elemwise_binary_broadcast_op_logic.cu | 18 +-
src/operator/tensor/elemwise_binary_op.cc | 351 ++-
src/operator/tensor/elemwise_binary_op.h | 192 +-
src/operator/tensor/elemwise_binary_op_basic.cu | 28 +-
src/operator/tensor/elemwise_binary_op_extended.cu | 22 +-
src/operator/tensor/elemwise_binary_op_logic.cu | 19 +-
src/operator/tensor/elemwise_binary_scalar_op.cc | 257 +++
src/operator/tensor/elemwise_binary_scalar_op.h | 91 +-
.../tensor/elemwise_binary_scalar_op_basic.cu | 37 +-
.../tensor/elemwise_binary_scalar_op_extended.cu | 29 +-
.../tensor/elemwise_binary_scalar_op_logic.cu | 30 +-
src/operator/tensor/elemwise_scatter_op.cc | 142 --
src/operator/tensor/elemwise_scatter_op.cu | 47 -
src/operator/tensor/elemwise_scatter_op.h | 318 ---
src/operator/tensor/elemwise_sum.cc | 15 +-
src/operator/tensor/elemwise_sum.cu | 113 +-
src/operator/tensor/elemwise_sum.h | 12 -
src/operator/tensor/elemwise_unary_op.cc | 163 ++
src/operator/tensor/elemwise_unary_op.h | 289 +--
src/operator/tensor/elemwise_unary_op_basic.cc | 4 +-
src/operator/tensor/elemwise_unary_op_basic.cu | 85 +-
src/operator/tensor/elemwise_unary_op_logexp.cu | 31 +-
src/operator/tensor/elemwise_unary_op_pow.cu | 35 +-
src/operator/tensor/elemwise_unary_op_trig.cu | 91 +-
src/operator/tensor/histogram.cc | 4 +-
src/operator/tensor/indexing_op.cc | 10 +-
src/operator/tensor/indexing_op.cu | 84 +-
src/operator/tensor/indexing_op.h | 186 +-
src/operator/tensor/init_op.h | 4 +-
src/operator/tensor/la_op-inl.h | 11 +-
src/operator/tensor/matrix_op-inl.h | 150 +-
src/operator/tensor/matrix_op.cc | 128 +-
src/operator/tensor/matrix_op.cu | 218 +-
src/operator/tensor/ordering_op-inl.h | 18 +
src/operator/tensor/pseudo2DTranspose_op-inl.cuh | 2 +-
src/operator/tensor/reduce_rtc.cc | 524 +++++
src/operator/tvmop/op_module.cc | 6 +
src/operator/tvmop/op_module.h | 2 +
src/profiler/aggregate_stats.cc | 4 +-
src/profiler/profiler.cc | 8 +-
src/profiler/storage_profiler.cc | 18 +-
src/profiler/storage_profiler.h | 20 +-
src/resource.cc | 119 +-
src/runtime/c_runtime_api.cc | 183 +-
src/runtime/registry.cc | 2 +-
src/storage/cpu_device_storage.h | 24 +-
src/storage/cpu_shared_storage_manager.h | 16 +-
src/storage/gpu_device_storage.h | 37 +-
src/storage/naive_storage_manager.h | 1 -
src/storage/pinned_memory_storage.h | 20 +-
src/storage/pooled_storage_manager.h | 593 ++---
src/storage/storage.cc | 272 ++-
src/storage/storage_manager.h | 2 +-
src/storage/storage_manager_helpers.h | 174 ++
tests/README.md | 9 +-
tests/cpp/engine/thread_local_test.cc | 2 +-
tests/cpp/engine/threaded_engine_test.cc | 8 +-
tests/cpp/operator/batchnorm_test.cc | 21 +-
tests/cpp/operator/mkldnn_test.cc | 2 +-
tests/cpp/operator/runner/core_op_runner_test.cc | 10 +-
tests/cpp/storage/storage_test.cc | 25 +-
tests/cpp/unittest.mk | 81 -
tests/jenkins/run_test.sh | 56 -
tests/jenkins/run_test_amzn_linux_gpu.sh | 65 -
tests/jenkins/run_test_ubuntu.sh | 65 -
tests/nightly/apache_rat_license_check/README.md | 2 +-
.../nightly/apache_rat_license_check/rat-excludes | 1 +
tests/nightly/common.py | 100 +
tests/nightly/download.sh | 38 -
tests/nightly/estimator/test_estimator_cnn.py | 7 +-
tests/nightly/estimator/test_sentiment_rnn.py | 7 +-
tests/nightly/test_large_array.py | 3 -
tests/nightly/test_large_vector.py | 3 -
tests/nightly/test_np_large_array.py | 2275 +++++++++++++++++++
tests/nightly/test_np_random.py | 11 +-
tests/python/gpu/test_amp.py | 194 ++
tests/python/gpu/test_contrib_amp.py | 204 --
tests/python/gpu/test_device.py | 16 +-
tests/python/gpu/test_fusion.py | 66 +-
tests/python/gpu/test_gluon_contrib_gpu.py | 87 -
tests/python/gpu/test_gluon_gpu.py | 106 +-
tests/python/gpu/test_gluon_model_zoo_gpu.py | 7 +-
tests/python/gpu/test_gluon_transforms.py | 6 +-
tests/python/gpu/test_kvstore_gpu.py | 12 +-
tests/python/gpu/test_numpy_fallback.py | 3 +-
tests/python/gpu/test_numpy_op.py | 158 ++
tests/python/gpu/test_operator_gpu.py | 506 ++---
tests/python/gpu/test_profiler_gpu.py | 189 ++
tests/python/gpu/test_tvm_op_gpu.py | 1 -
tests/python/mkl/test_amp.py | 166 ++
tests/python/mkl/test_bf16_operator.py | 15 +-
tests/python/mkl/test_contrib_amp.py | 169 --
tests/python/mkl/test_mkldnn.py | 54 +-
tests/python/mkl/test_subgraph.py | 1 -
tests/python/unittest/common.py | 163 +-
tests/python/unittest/onnx/backend_test.py | 51 +-
tests/python/unittest/onnx/mxnet_export_test.py | 17 +-
tests/python/unittest/onnx/test_node.py | 8 +-
tests/python/unittest/test_autograd.py | 86 +-
tests/python/unittest/test_base.py | 105 +-
tests/python/unittest/test_contrib_autograd.py | 193 --
tests/python/unittest/test_contrib_control_flow.py | 13 +-
.../unittest/test_contrib_gluon_data_vision.py | 4 +-
tests/python/unittest/test_contrib_intgemm.py | 215 ++
tests/python/unittest/test_contrib_operator.py | 87 +-
tests/python/unittest/test_contrib_optimizer.py | 3 +-
tests/python/unittest/test_contrib_stes_op.py | 4 +-
tests/python/unittest/test_contrib_text.py | 794 -------
tests/python/unittest/test_deferred_compute.py | 96 +-
tests/python/unittest/test_dlpack.py | 45 -
tests/python/unittest/test_dynamic_shape.py | 1 -
tests/python/unittest/test_engine.py | 4 +-
tests/python/unittest/test_engine_import.py | 14 +-
tests/python/unittest/test_exc_handling.py | 12 -
tests/python/unittest/test_executor.py | 71 +-
tests/python/unittest/test_gluon.py | 508 +++--
tests/python/unittest/test_gluon_contrib.py | 426 ----
tests/python/unittest/test_gluon_data.py | 39 +-
tests/python/unittest/test_gluon_data_vision.py | 57 +-
tests/python/unittest/test_gluon_estimator.py | 4 +-
tests/python/unittest/test_gluon_indexing.py | 104 +
tests/python/unittest/test_gluon_model_zoo.py | 5 +-
tests/python/unittest/test_gluon_probability_v1.py | 2400 ++++++++++++++++++++
tests/python/unittest/test_gluon_probability_v2.py | 2332 +++++++++++++++++++
tests/python/unittest/test_gluon_rnn.py | 299 ++-
tests/python/unittest/test_gluon_trainer.py | 68 +-
tests/python/unittest/test_higher_order_grad.py | 33 +-
tests/python/unittest/test_image.py | 20 +-
tests/python/unittest/test_infer_type.py | 4 +-
tests/python/unittest/test_io.py | 54 +-
tests/python/unittest/test_kvstore.py | 12 +-
tests/python/unittest/test_kvstore_custom.py | 9 +-
tests/python/unittest/test_loss.py | 35 +-
tests/python/unittest/test_memory_opt.py | 43 +-
tests/python/unittest/test_metric.py | 22 +-
tests/python/unittest/test_ndarray.py | 60 +-
.../test_numpy_contrib_gluon_data_vision.py | 8 +-
tests/python/unittest/test_numpy_default_dtype.py | 7 -
tests/python/unittest/test_numpy_gluon.py | 131 +-
.../unittest/test_numpy_gluon_data_vision.py | 37 +-
.../python/unittest/test_numpy_interoperability.py | 88 +-
tests/python/unittest/test_numpy_loss.py | 310 +++
tests/python/unittest/test_numpy_ndarray.py | 77 +-
tests/python/unittest/test_numpy_op.py | 904 ++++----
tests/python/unittest/test_operator.py | 658 +++---
tests/python/unittest/test_optimizer.py | 26 +-
tests/python/unittest/test_profiler.py | 124 +-
tests/python/unittest/test_random.py | 28 +-
tests/python/unittest/test_recordio.py | 4 -
tests/python/unittest/test_runtime.py | 5 +-
tests/python/unittest/test_smoke.py | 94 +
tests/python/unittest/test_sparse_ndarray.py | 54 +-
tests/python/unittest/test_sparse_operator.py | 173 +-
tests/python/unittest/test_subgraph.py | 2 -
tests/python/unittest/test_subgraph_op.py | 98 +-
tests/python/unittest/test_symbol.py | 78 +-
tests/python/unittest/test_thread_local.py | 153 +-
tests/python/unittest/test_tvm_op.py | 2 -
tools/dependencies/cityhash.sh | 7 +
tools/dependencies/libpng.sh | 3 +-
tools/dependencies/libturbojpeg.sh | 4 +-
tools/dependencies/lz4.sh | 7 +
tools/dependencies/openblas.sh | 27 +-
tools/dependencies/opencv.sh | 2 +-
tools/dependencies/openssl.sh | 4 +-
tools/dependencies/zmq.sh | 9 +
tools/im2rec.cc | 2 +-
tools/license_header.py | 7 +-
tools/pip/doc/CPU_ADDITIONAL.md | 13 +-
tools/pip/doc/CU100_ADDITIONAL.md | 37 -
tools/pip/doc/CU101_ADDITIONAL.md | 14 +-
tools/pip/doc/CU102_ADDITIONAL.md | 14 +-
tools/pip/doc/CU110_ADDITIONAL.md | 43 +
tools/pip/doc/CU92_ADDITIONAL.md | 36 -
tools/pip/doc/NATIVE_ADDITIONAL.md | 13 +-
tools/pip/setup.py | 56 +-
tools/setup_gpu_build_tools.sh | 204 --
tools/staticbuild/README.md | 15 +-
tools/staticbuild/build.sh | 17 +-
tools/staticbuild/build_lib.sh | 36 +-
tools/staticbuild/build_lib_cmake.sh | 62 -
tools/windowsbuild/warp_dll.cpp | 7 +-
1073 files changed, 60892 insertions(+), 41924 deletions(-)
create mode 100644 .asf.yaml
create mode 100644 .github/ISSUE_TEMPLATE/rfc.md
create mode 100644 .github/workflows/greetings.yml
create mode 160000 3rdparty/intgemm
delete mode 100644 3rdparty/mshadow/mshadow/half2.h
delete mode 100644 Makefile
delete mode 100644 ci/docker/Dockerfile.build.ubuntu_cpu_c
delete mode 100644 ci/docker/Dockerfile.build.ubuntu_cpu_julia
delete mode 100644 ci/docker/Dockerfile.build.ubuntu_cpu_lite
delete mode 100644 ci/docker/Dockerfile.build.ubuntu_cpu_python
delete mode 100644 ci/docker/Dockerfile.build.ubuntu_cpu_r
delete mode 100644 ci/docker/Dockerfile.build.ubuntu_cpu_scala
delete mode 100644 ci/docker/Dockerfile.build.ubuntu_gpu_tensorrt
delete mode 100644 ci/docker/Dockerfile.build.ubuntu_rat
delete mode 100644 ci/docker/Dockerfile.publish.test.ubuntu1604_cpu
delete mode 100644 ci/docker/Dockerfile.publish.test.ubuntu1604_gpu
delete mode 100644 ci/docker/Dockerfile.publish.test.ubuntu1804_cpu
delete mode 100644 ci/docker/Dockerfile.publish.test.ubuntu1804_gpu
delete mode 100644 ci/docker/Dockerfile.publish.ubuntu1604_cpu
delete mode 100644 ci/docker/Dockerfile.publish.ubuntu1604_gpu
delete mode 100755 ci/docker/install/export_gpg_keys.sh
delete mode 100644 ci/docker/install/r.gpg
delete mode 100644 ci/docker/install/sbt.gpg
delete mode 100755 ci/docker/install/tensorrt.sh
delete mode 100755 ci/docker/install/ubuntu_base.sh
delete mode 100755 ci/docker/install/ubuntu_clang.sh
delete mode 100755 ci/docker/install/ubuntu_clojure.sh
delete mode 100755 ci/docker/install/ubuntu_cudnn.sh
delete mode 100755 ci/docker/install/ubuntu_docs.sh
delete mode 100755 ci/docker/install/ubuntu_emscripten.sh
delete mode 100755 ci/docker/install/ubuntu_gcc8.sh
delete mode 100755 ci/docker/install/ubuntu_julia.sh
delete mode 100755 ci/docker/install/ubuntu_nightly_tests.sh
delete mode 100755 ci/docker/install/ubuntu_r.sh
delete mode 100755 ci/docker/install/ubuntu_rat.sh
delete mode 100755 ci/docker/install/ubuntu_scala.sh
delete mode 100644 ci/docker_cache.py
delete mode 100644 ci/docker_cache_requirements
delete mode 100644 ci/jenkins/Jenkinsfile_website_c_docs
delete mode 100644 ci/jenkins/Jenkinsfile_website_clojure_docs
delete mode 100644 ci/jenkins/Jenkinsfile_website_java_docs
delete mode 100644 ci/jenkins/Jenkinsfile_website_julia_docs
delete mode 100644 ci/test_docker_cache.py
delete mode 100644 ci/windows/test_jl07_cpu.ps1
delete mode 100644 ci/windows/test_jl10_cpu.ps1
create mode 100644 cmake/Modules/FindCUTENSOR.cmake
create mode 100644 cmake/libmxnet.sym
create mode 100644 cmake/libmxnet.ver
create mode 100644 config/distribution/darwin_native.cmake
create mode 100644 config/distribution/linux_cu110.cmake
create mode 100644 doap.rdf
create mode 100644 docs/python_docs/_static/feedback.css
create mode 100644 docs/python_docs/_static/transformer.png
delete mode 100644 docs/python_docs/environment.yml
rename docs/python_docs/python/api/{mxnet => }/context/index.rst (100%)
delete mode 100644 docs/python_docs/python/api/contrib/autograd/index.rst
delete mode 100644 docs/python_docs/python/api/contrib/quantization/index.rst
rename docs/python_docs/python/api/{mxnet => }/engine/index.rst (100%)
rename docs/python_docs/python/api/{mxnet => }/executor/index.rst (100%)
create mode 100644 docs/python_docs/python/api/gluon/metric/index.rst
delete mode 100644 docs/python_docs/python/api/gluon/parameter_dict.rst
rename docs/python_docs/python/api/{mxnet => }/kvstore_server/index.rst (100%)
create mode 100644 docs/python_docs/python/api/legacy/callback/index.rst
rename docs/python_docs/python/api/{mxnet => legacy}/image/index.rst (100%)
create mode 100644 docs/python_docs/python/api/legacy/index.rst
rename docs/python_docs/python/api/{mxnet => legacy}/io/index.rst (100%)
create mode 100644 docs/python_docs/python/api/legacy/ndarray/contrib/index.rst
create mode 100644 docs/python_docs/python/api/legacy/ndarray/image/index.rst
rename docs/python_docs/python/api/{ => legacy}/ndarray/index.rst (100%)
create mode 100644 docs/python_docs/python/api/legacy/ndarray/linalg/index.rst
create mode 100644 docs/python_docs/python/api/legacy/ndarray/ndarray.rst
create mode 100644 docs/python_docs/python/api/legacy/ndarray/op/index.rst
create mode 100644 docs/python_docs/python/api/legacy/ndarray/random/index.rst
create mode 100644 docs/python_docs/python/api/legacy/ndarray/register/index.rst
create mode 100644 docs/python_docs/python/api/legacy/ndarray/sparse/index.rst
create mode 100644 docs/python_docs/python/api/legacy/ndarray/utils/index.rst
rename docs/python_docs/python/api/{mxnet => legacy}/recordio/index.rst (100%)
rename docs/python_docs/python/api/{ => legacy}/symbol/contrib/index.rst (100%)
rename docs/python_docs/python/api/{ => legacy}/symbol/image/index.rst (100%)
rename docs/python_docs/python/api/{ => legacy}/symbol/index.rst (100%)
rename docs/python_docs/python/api/{ => legacy}/symbol/linalg/index.rst (100%)
rename docs/python_docs/python/api/{ => legacy}/symbol/op/index.rst (100%)
rename docs/python_docs/python/api/{ => legacy}/symbol/random/index.rst (100%)
rename docs/python_docs/python/api/{ => legacy}/symbol/register/index.rst (100%)
rename docs/python_docs/python/api/{ => legacy}/symbol/sparse/index.rst (100%)
rename docs/python_docs/python/api/{ => legacy}/symbol/symbol.rst (100%)
rename docs/python_docs/python/api/{mxnet => legacy}/visualization/index.rst (100%)
delete mode 100644 docs/python_docs/python/api/metric/index.rst
delete mode 100644 docs/python_docs/python/api/module/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/attribute/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/base/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/callback/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/executor_manager/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/libinfo/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/log/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/model/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/monitor/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/name/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/notebook/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/operator/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/random/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/registry/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/runtime/index.rst
delete mode 100644 docs/python_docs/python/api/mxnet/torch/index.rst
delete mode 100644 docs/python_docs/python/api/ndarray/contrib/index.rst
delete mode 100644 docs/python_docs/python/api/ndarray/image/index.rst
delete mode 100644 docs/python_docs/python/api/ndarray/linalg/index.rst
delete mode 100644 docs/python_docs/python/api/ndarray/ndarray.rst
delete mode 100644 docs/python_docs/python/api/ndarray/op/index.rst
delete mode 100644 docs/python_docs/python/api/ndarray/random/index.rst
delete mode 100644 docs/python_docs/python/api/ndarray/register/index.rst
delete mode 100644 docs/python_docs/python/api/ndarray/sparse/index.rst
delete mode 100644 docs/python_docs/python/api/ndarray/utils/index.rst
create mode 100644 docs/python_docs/python/api/np/arrays.indexing.rst
create mode 100644 docs/python_docs/python/api/np/arrays.ndarray.rst
create mode 100644 docs/python_docs/python/api/np/arrays.rst
create mode 100644 docs/python_docs/python/api/np/index.rst
create mode 100644 docs/python_docs/python/api/np/random/index.rst
create mode 100644 docs/python_docs/python/api/np/routines.array-creation.rst
create mode 100644 docs/python_docs/python/api/np/routines.array-manipulation.rst
create mode 100644 docs/python_docs/python/api/np/routines.io.rst
create mode 100644 docs/python_docs/python/api/np/routines.linalg.rst
create mode 100644 docs/python_docs/python/api/np/routines.math.rst
create mode 100644 docs/python_docs/python/api/np/routines.rst
create mode 100644 docs/python_docs/python/api/np/routines.sort.rst
create mode 100644 docs/python_docs/python/api/np/routines.statistics.rst
create mode 100644 docs/python_docs/python/api/npx/index.rst
rename docs/python_docs/python/api/{mxnet => }/profiler/index.rst (100%)
rename docs/python_docs/python/api/{mxnet => }/rtc/index.rst (100%)
create mode 100644 docs/python_docs/python/api/runtime/index.rst
rename docs/python_docs/python/api/{mxnet => }/test_utils/index.rst (100%)
rename docs/python_docs/python/api/{mxnet => }/util/index.rst (100%)
delete mode 100644 docs/python_docs/python/tutorials/deploy/inference/scala.rst
delete mode 100644 docs/python_docs/python/tutorials/extend/custom_layer.md
create mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/0-introduction.md
delete mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/1-ndarray.md
create mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/1-nparray.md
create mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/2-create-nn.md
delete mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/2-nn.md
create mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/4-components.md
delete mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/4-train.md
create mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/5-datasets.md
delete mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/5-predict.md
create mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/6-train-nn.md
delete mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/6-use_gpus.md
create mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/7-use-gpus.md
create mode 100644 docs/python_docs/python/tutorials/getting-started/crash-course/prepare_dataset.py
delete mode 100644 docs/python_docs/python/tutorials/packages/gluon/image/image-augmentation.md
delete mode 100644 docs/python_docs/python/tutorials/packages/gluon/image/pretrained_models.md
create mode 100644 docs/python_docs/python/tutorials/packages/legacy/index.rst
create mode 100644 docs/python_docs/python/tutorials/packages/legacy/ndarray/01-ndarray-intro.md
create mode 100644 docs/python_docs/python/tutorials/packages/legacy/ndarray/02-ndarray-operations.md
rename docs/python_docs/python/tutorials/packages/{ => legacy}/ndarray/03-ndarray-contexts.md (100%)
create mode 100644 docs/python_docs/python/tutorials/packages/legacy/ndarray/gotchas_numpy_in_mxnet.md
create mode 100644 docs/python_docs/python/tutorials/packages/legacy/ndarray/index.rst
create mode 100644 docs/python_docs/python/tutorials/packages/legacy/ndarray/sparse/csr.md
rename docs/python_docs/python/tutorials/packages/{ => legacy}/ndarray/sparse/index.rst (100%)
create mode 100644 docs/python_docs/python/tutorials/packages/legacy/ndarray/sparse/row_sparse.md
create mode 100644 docs/python_docs/python/tutorials/packages/legacy/ndarray/sparse/train_gluon.md
delete mode 100644 docs/python_docs/python/tutorials/packages/ndarray/01-ndarray-intro.md
delete mode 100644 docs/python_docs/python/tutorials/packages/ndarray/02-ndarray-operations.md
delete mode 100644 docs/python_docs/python/tutorials/packages/ndarray/gotchas_numpy_in_mxnet.md
delete mode 100644 docs/python_docs/python/tutorials/packages/ndarray/index.rst
delete mode 100644 docs/python_docs/python/tutorials/packages/ndarray/sparse/csr.md
delete mode 100644 docs/python_docs/python/tutorials/packages/ndarray/sparse/row_sparse.md
delete mode 100644 docs/python_docs/python/tutorials/packages/ndarray/sparse/train_gluon.md
create mode 100644 docs/python_docs/python/tutorials/packages/np/cheat-sheet.md
create mode 100644 docs/python_docs/python/tutorials/packages/np/index.rst
create mode 100644 docs/python_docs/python/tutorials/packages/np/np-vs-numpy.md
delete mode 100644 docs/python_docs/python/tutorials/performance/backend/tensorrt/index.rst
delete mode 100644 docs/python_docs/python/tutorials/performance/backend/tensorrt/wavenet_optimized.svg
delete mode 100644 docs/python_docs/python/tutorials/performance/backend/tensorrt/wavenet_unoptimized.svg
create mode 100644 docs/python_docs/requirements
create mode 100644 docs/python_docs/themes/mx-theme/mxtheme/feedback.html
create mode 100644 docs/python_docs/themes/mx-theme/src/js/feedback.js
create mode 100644 docs/static_site/src/_includes/callout.html
create mode 100644 docs/static_site/src/_includes/feedback.html
create mode 100644 docs/static_site/src/_includes/important.html
create mode 100644 docs/static_site/src/_includes/note.html
create mode 100644 docs/static_site/src/_includes/tip.html
create mode 100644 docs/static_site/src/_includes/warning.html
create mode 100644 docs/static_site/src/_sass/feedback.scss
create mode 100644 docs/static_site/src/assets/img/autogluon.png
create mode 100644 docs/static_site/src/assets/img/tune.png
create mode 100644 docs/static_site/src/assets/js/feedback.js
delete mode 100644 docs/static_site/src/pages/api/faq/caffe.md
delete mode 100644 docs/static_site/src/pages/api/faq/nnpack.md
create mode 100644 docs/static_site/src/pages/api/faq/using_rtc.md
create mode 100644 docs/static_site/src/pages/community/code_guide.md
create mode 100644 docs/static_site/src/pages/community/code_review.md
create mode 100644 docs/static_site/src/pages/community/committer_guide.md
create mode 100644 docs/static_site/src/pages/community/community.md
delete mode 100644 docs/static_site/src/pages/community/contribute.md
create mode 100644 docs/static_site/src/pages/community/document.md
create mode 100644 docs/static_site/src/pages/community/error_handling.md
create mode 100644 docs/static_site/src/pages/community/git_howto.md
create mode 100644 docs/static_site/src/pages/community/index.md
create mode 100644 docs/static_site/src/pages/community/pull_request.md
create mode 100644 example/extensions/lib_custom_op/relu_lib.cc
create mode 100644 example/extensions/lib_custom_op/relu_lib.h
create mode 100644 example/extensions/lib_pass/example_connection.png
create mode 100644 example/probability/VAE/VAE.md
create mode 100644 example/probability/VAE/VAE_11_0.png
create mode 100644 example/probability/VAE/VAE_14_0.png
delete mode 100644 make/config.mk
delete mode 100644 make/config/libmxnet.sym
delete mode 100644 make/config/libmxnet.ver
delete mode 100644 make/config_jetson.mk
delete mode 100644 make/osx.mk
delete mode 100644 make/readthedocs.mk
delete mode 100644 make/staticbuild/darwin_cpu.mk
delete mode 100644 make/staticbuild/darwin_mkl.mk
delete mode 100644 make/staticbuild/linux_cpu.mk
delete mode 100644 make/staticbuild/linux_cu100.mk
delete mode 100644 make/staticbuild/linux_cu101.mk
delete mode 100644 make/staticbuild/linux_cu102.mk
delete mode 100644 make/staticbuild/linux_cu92.mk
delete mode 100644 make/staticbuild/linux_native.mk
delete mode 100644 mkldnn.mk
delete mode 100644 plugin/caffe/README.md
delete mode 100644 plugin/caffe/caffe.mk
delete mode 100644 plugin/caffe/caffe_blob.cc
delete mode 100644 plugin/caffe/caffe_blob.h
delete mode 100644 plugin/caffe/caffe_common.cc
delete mode 100644 plugin/caffe/caffe_common.h
delete mode 100644 plugin/caffe/caffe_data_iter.cc
delete mode 100644 plugin/caffe/caffe_fieldentry.h
delete mode 100644 plugin/caffe/caffe_loss-inl.h
delete mode 100644 plugin/caffe/caffe_loss.cc
delete mode 100644 plugin/caffe/caffe_loss.cu
delete mode 100644 plugin/caffe/caffe_op-inl.h
delete mode 100644 plugin/caffe/caffe_op.cc
delete mode 100644 plugin/caffe/caffe_op.cu
delete mode 100644 plugin/caffe/caffe_stream.cc
delete mode 100644 plugin/caffe/caffe_stream.h
rename python/mxnet/{contrib => }/amp/__init__.py (100%)
create mode 100644 python/mxnet/amp/amp.py
rename python/mxnet/{contrib => }/amp/lists/__init__.py (100%)
create mode 100644 python/mxnet/amp/lists/symbol_bf16.py
create mode 100644 python/mxnet/amp/lists/symbol_fp16.py
create mode 100644 python/mxnet/amp/loss_scaler.py
delete mode 100644 python/mxnet/contrib/amp/amp.py
delete mode 100644 python/mxnet/contrib/amp/lists/symbol_bf16.py
delete mode 100644 python/mxnet/contrib/amp/lists/symbol_fp16.py
delete mode 100644 python/mxnet/contrib/amp/loss_scaler.py
delete mode 100644 python/mxnet/contrib/autograd.py
create mode 100644 python/mxnet/dlpack.py
delete mode 100644 python/mxnet/gluon/contrib/cnn/__init__.py
delete mode 100644 python/mxnet/gluon/contrib/cnn/conv_layers.py
delete mode 100644 python/mxnet/gluon/contrib/data/sampler.py
delete mode 100644 python/mxnet/gluon/contrib/data/text.py
delete mode 100644 python/mxnet/gluon/contrib/nn/__init__.py
delete mode 100644 python/mxnet/gluon/contrib/nn/basic_layers.py
delete mode 100644 python/mxnet/gluon/contrib/rnn/__init__.py
delete mode 100644 python/mxnet/gluon/contrib/rnn/conv_rnn_cell.py
delete mode 100644 python/mxnet/gluon/contrib/rnn/rnn_cell.py
create mode 100644 python/mxnet/gluon/probability/__init__.py
create mode 100644 python/mxnet/gluon/probability/block/__init__.py
create mode 100644 python/mxnet/gluon/probability/block/stochastic_block.py
create mode 100644 python/mxnet/gluon/probability/distributions/__init__.py
create mode 100644 python/mxnet/gluon/probability/distributions/bernoulli.py
create mode 100644 python/mxnet/gluon/probability/distributions/beta.py
create mode 100644 python/mxnet/gluon/probability/distributions/binomial.py
create mode 100644 python/mxnet/gluon/probability/distributions/categorical.py
create mode 100644 python/mxnet/gluon/probability/distributions/cauchy.py
create mode 100644 python/mxnet/gluon/probability/distributions/chi2.py
create mode 100644 python/mxnet/gluon/probability/distributions/constraint.py
create mode 100644 python/mxnet/gluon/probability/distributions/dirichlet.py
create mode 100644 python/mxnet/gluon/probability/distributions/distribution.py
create mode 100644 python/mxnet/gluon/probability/distributions/divergence.py
create mode 100644 python/mxnet/gluon/probability/distributions/exp_family.py
create mode 100644 python/mxnet/gluon/probability/distributions/exponential.py
create mode 100644 python/mxnet/gluon/probability/distributions/fishersnedecor.py
create mode 100644 python/mxnet/gluon/probability/distributions/gamma.py
create mode 100644 python/mxnet/gluon/probability/distributions/geometric.py
create mode 100644 python/mxnet/gluon/probability/distributions/gumbel.py
create mode 100644 python/mxnet/gluon/probability/distributions/half_cauchy.py
create mode 100644 python/mxnet/gluon/probability/distributions/half_normal.py
create mode 100644 python/mxnet/gluon/probability/distributions/independent.py
create mode 100644 python/mxnet/gluon/probability/distributions/laplace.py
create mode 100644 python/mxnet/gluon/probability/distributions/multinomial.py
create mode 100644 python/mxnet/gluon/probability/distributions/multivariate_normal.py
create mode 100644 python/mxnet/gluon/probability/distributions/negative_binomial.py
create mode 100644 python/mxnet/gluon/probability/distributions/normal.py
create mode 100644 python/mxnet/gluon/probability/distributions/one_hot_categorical.py
create mode 100644 python/mxnet/gluon/probability/distributions/pareto.py
create mode 100644 python/mxnet/gluon/probability/distributions/poisson.py
create mode 100644 python/mxnet/gluon/probability/distributions/relaxed_bernoulli.py
create mode 100644 python/mxnet/gluon/probability/distributions/relaxed_one_hot_categorical.py
create mode 100644 python/mxnet/gluon/probability/distributions/studentT.py
create mode 100644 python/mxnet/gluon/probability/distributions/transformed_distribution.py
create mode 100644 python/mxnet/gluon/probability/distributions/uniform.py
create mode 100644 python/mxnet/gluon/probability/distributions/utils.py
create mode 100644 python/mxnet/gluon/probability/distributions/weibull.py
create mode 100644 python/mxnet/gluon/probability/transformation/__init__.py
create mode 100644 python/mxnet/gluon/probability/transformation/domain_map.py
create mode 100644 python/mxnet/gluon/probability/transformation/transformation.py
create mode 100644 python/mxnet/gluon/rnn/conv_rnn_cell.py
delete mode 100644 python/mxnet/torch.py
delete mode 100644 setup-utils/install-mxnet-amz-linux.sh
delete mode 100644 setup-utils/install-mxnet-fedora-python.sh
delete mode 100755 setup-utils/install-mxnet-osx-python.sh
delete mode 100644 setup-utils/install-mxnet-ubuntu-python.sh
delete mode 100644 setup-utils/install-mxnet-ubuntu-r.sh
delete mode 100755 setup-utils/install-mxnet-virtualenv.sh
delete mode 100644 setup-utils/install-mxnet-windows-python.bat
create mode 100644 src/api/operator/numpy/np_dot_op.cc
create mode 100644 src/api/operator/numpy/np_ordering_op.cc
create mode 100644 src/api/operator/numpy/random/np_multinomial_op.cc
delete mode 100644 src/c_api/c_api_error.cc
create mode 100644 src/common/cuda/rtc.cc
create mode 100644 src/common/cuda/rtc.h
create mode 100644 src/common/cuda/rtc/backward_functions-inl.h
create mode 100644 src/common/cuda/rtc/forward_functions-inl.h
create mode 100644 src/common/cuda/rtc/half-inl.h
create mode 100644 src/common/cuda/rtc/reducer-inl.h
create mode 100644 src/common/cuda/rtc/special_functions-inl.h
create mode 100644 src/common/cuda/rtc/util-inl.h
create mode 100644 src/common/cuda/rtc/vectorization-inl.h
create mode 100644 src/common/cuda/utils.cc
create mode 100644 src/common/cuda/utils.h
delete mode 100644 src/common/cuda_utils.cc
delete mode 100644 src/common/cuda_utils.h
create mode 100644 src/imperative/simple_partition_pass.cc
create mode 100644 src/lib_api.cc
create mode 100644 src/operator/all_finite-inl.h
create mode 100644 src/operator/all_finite.cc
rename src/operator/{contrib => }/all_finite.cu (100%)
mode change 100755 => 100644
rename src/operator/{contrib => }/amp_graph_pass.cc (100%)
delete mode 100755 src/operator/contrib/all_finite-inl.h
delete mode 100755 src/operator/contrib/all_finite.cc
delete mode 100644 src/operator/contrib/deformable_convolution-inl.h
delete mode 100644 src/operator/contrib/deformable_convolution.cc
create mode 100644 src/operator/contrib/dynamic_shape_ops-inl.h
create mode 100644 src/operator/contrib/dynamic_shape_ops.cc
create mode 100644 src/operator/contrib/intgemm/intgemm_fully_connected_op.cc
create mode 100644 src/operator/contrib/intgemm/max_absolute_op.cc
create mode 100644 src/operator/contrib/intgemm/prepare_data_op.cc
create mode 100644 src/operator/contrib/intgemm/prepare_weight_op.cc
create mode 100644 src/operator/contrib/intgemm/take_weight_op.cc
delete mode 100644 src/operator/contrib/modulated_deformable_convolution-inl.h
delete mode 100644 src/operator/contrib/modulated_deformable_convolution.cc
delete mode 100644 src/operator/convolution_v1-inl.h
delete mode 100644 src/operator/convolution_v1.cc
delete mode 100644 src/operator/convolution_v1.cu
create mode 100644 src/operator/deformable_convolution-inl.h
create mode 100644 src/operator/deformable_convolution.cc
rename src/operator/{contrib => }/deformable_convolution.cu (100%)
create mode 100644 src/operator/modulated_deformable_convolution-inl.h
create mode 100644 src/operator/modulated_deformable_convolution.cc
rename src/operator/{contrib => }/modulated_deformable_convolution.cu (100%)
delete mode 100644 src/operator/nnpack/nnpack_convolution-inl.h
delete mode 100644 src/operator/nnpack/nnpack_fully_connected-inl.h
delete mode 100644 src/operator/nnpack/nnpack_pooling-inl.h
delete mode 100644 src/operator/nnpack/nnpack_util.cc
delete mode 100644 src/operator/nnpack/nnpack_util.h
create mode 100644 src/operator/numpy/np_broadcast_reduce_op.cuh
create mode 100644 src/operator/numpy/np_indexing_op.cc
create mode 100644 src/operator/numpy/np_indexing_op.cu
create mode 100644 src/operator/numpy/np_indexing_op.h
delete mode 100644 src/operator/pooling_v1-inl.h
delete mode 100644 src/operator/pooling_v1.cc
delete mode 100644 src/operator/pooling_v1.cu
delete mode 100644 src/operator/tensor/elemwise_binary_broadcast_op-inl.cuh
create mode 100644 src/operator/tensor/elemwise_binary_broadcast_op.cc
create mode 100644 src/operator/tensor/elemwise_binary_scalar_op.cc
delete mode 100644 src/operator/tensor/elemwise_scatter_op.cc
delete mode 100644 src/operator/tensor/elemwise_scatter_op.cu
delete mode 100644 src/operator/tensor/elemwise_scatter_op.h
create mode 100644 src/operator/tensor/elemwise_unary_op.cc
create mode 100644 src/operator/tensor/reduce_rtc.cc
create mode 100644 src/storage/storage_manager_helpers.h
delete mode 100644 tests/cpp/unittest.mk
delete mode 100755 tests/jenkins/run_test.sh
delete mode 100755 tests/jenkins/run_test_amzn_linux_gpu.sh
delete mode 100755 tests/jenkins/run_test_ubuntu.sh
create mode 100644 tests/nightly/common.py
delete mode 100644 tests/nightly/download.sh
create mode 100644 tests/nightly/test_np_large_array.py
create mode 100644 tests/python/gpu/test_amp.py
delete mode 100644 tests/python/gpu/test_contrib_amp.py
delete mode 100644 tests/python/gpu/test_gluon_contrib_gpu.py
create mode 100644 tests/python/gpu/test_numpy_op.py
create mode 100644 tests/python/gpu/test_profiler_gpu.py
create mode 100644 tests/python/mkl/test_amp.py
delete mode 100644 tests/python/mkl/test_contrib_amp.py
delete mode 100644 tests/python/unittest/test_contrib_autograd.py
create mode 100644 tests/python/unittest/test_contrib_intgemm.py
delete mode 100644 tests/python/unittest/test_contrib_text.py
delete mode 100644 tests/python/unittest/test_dlpack.py
delete mode 100644 tests/python/unittest/test_gluon_contrib.py
create mode 100644 tests/python/unittest/test_gluon_indexing.py
create mode 100644 tests/python/unittest/test_gluon_probability_v1.py
create mode 100644 tests/python/unittest/test_gluon_probability_v2.py
create mode 100644 tests/python/unittest/test_numpy_loss.py
create mode 100644 tests/python/unittest/test_smoke.py
delete mode 100644 tools/pip/doc/CU100_ADDITIONAL.md
create mode 100644 tools/pip/doc/CU110_ADDITIONAL.md
delete mode 100644 tools/pip/doc/CU92_ADDITIONAL.md
delete mode 100755 tools/setup_gpu_build_tools.sh
delete mode 100755 tools/staticbuild/build_lib_cmake.sh