Junhwan Kim [Fri, 25 Jun 2021 06:40:16 +0000 (15:40 +0900)]
[Debian] Update debian packaging
Change-Id: Ic600268b571cd25e7457f284d813391a8dec8b11
Signed-off-by: Junhwan Kim <jejudo.kim@samsung.com>
Junhwan Kim [Fri, 25 Jun 2021 05:07:46 +0000 (14:07 +0900)]
[Tizen] Updated spec file
Change-Id: Idc7c9be256c17b49cfacb165044d4b6c2826de6e
Signed-off-by: Junhwan Kim <jejudo.kim@samsung.com>
Junhwan Kim [Fri, 25 Jun 2021 04:53:46 +0000 (13:53 +0900)]
[Tizen] Added submodule into working tree
Change-Id: I08abd47c9980dce3078125ac9984beac33394e63
Signed-off-by: Junhwan Kim <jejudo.kim@samsung.com>
Tianqi Chen [Thu, 29 Apr 2021 15:53:07 +0000 (11:53 -0400)]
[CI] v0.7 CI updates (#7947)
Qiang Zhang [Wed, 17 Feb 2021 14:22:32 +0000 (22:22 +0800)]
[Backport-0.7][Quantize] Fix Bug Which Cause Negative Left Shift Op (#7433)
Liangfu Chen [Thu, 24 Dec 2020 08:04:21 +0000 (16:04 +0800)]
[Backport-0.7][Android] missing header for GraphRuntimeFactory in android_rpc (#7160)
Cody Yu [Wed, 11 Nov 2020 02:18:11 +0000 (18:18 -0800)]
[Backport][TopHub] Bump the versions (#6896)
* [Backport][TopHub] Bump the versions
Junru Shao [Fri, 6 Nov 2020 19:22:52 +0000 (11:22 -0800)]
[Backport][Bugfix][Module] Fix recursive GetFunction in runtime::Module (#6866)
Tianqi Chen [Fri, 6 Nov 2020 19:22:40 +0000 (14:22 -0500)]
Update task_golang.sh
Tianqi Chen [Mon, 2 Nov 2020 13:55:36 +0000 (08:55 -0500)]
[FFI][BUGFIX] Fix memory leak when Pac callback argument is NDArray (#6744) (#6821)
Co-authored-by: Matthew Brookhart <mbrookhart@octoml.ai>
Co-authored-by: Junru Shao <junrushao1994@gmail.com>
Tianqi Chen [Mon, 2 Nov 2020 13:45:27 +0000 (08:45 -0500)]
Update stale link (#6820)
ziheng [Fri, 2 Oct 2020 16:45:23 +0000 (09:45 -0700)]
[RELEASE] Update NEWS.md for v0.7 (#6613)
Cody Yu [Fri, 2 Oct 2020 13:38:22 +0000 (06:38 -0700)]
[Ansor] Support multiple output ops and fix Python API printing (#6584)
iiahim [Fri, 2 Oct 2020 13:37:18 +0000 (06:37 -0700)]
Updated runtime to run under FreeBSD. (#6600)
* Updated runtime to run under FreeBSD.
setenv CXX to proper binary - c++ or g++9 for FreeBSD 12.0.
* Update python/tvm/runtime/module.py
Co-authored-by: Junru Shao <junrushao1994@gmail.com>
* Update python/tvm/rpc/server.py
Co-authored-by: Junru Shao <junrushao1994@gmail.com>
* Changed to use os.environ.get
* Fixed format.
* Yet another lint fix.
Co-authored-by: Junru Shao <junrushao1994@gmail.com>
Lily Orth-Smith [Fri, 2 Oct 2020 13:36:06 +0000 (06:36 -0700)]
[BUG_FIX] Fixes #6608: CHECK(data != nullptr) causes type checking to fail (#6610)
ziheng [Fri, 2 Oct 2020 13:35:49 +0000 (06:35 -0700)]
[RELEASE] Bump version to 0.7.0 (#6614)
Yizhi Liu [Fri, 2 Oct 2020 05:47:48 +0000 (22:47 -0700)]
[Bugfix] Simplify reduce expression in te.gradient (#6611)
Leandro Nunes [Fri, 2 Oct 2020 04:46:05 +0000 (05:46 +0100)]
[tvmc][docs] Getting started tutorial for TVMC (#6597)
* [tvmc][docs] Getting started tutorial for TVMC
* Include a tutorial, demonstrating basic capabilities of
TVMC, by executing a full pipeline (tune, compile, run)
on a ResNet-50 model.
Co-authored-by: Matthew Barrett <matthew.barrett@arm.com>
* apply suggestions from code review
Co-authored-by: Tristan Konolige <tristan.konolige@gmail.com>
Co-authored-by: Cody Yu <comaniac0422@gmail.com>
* adjust text according to code-review
* improve reading flow into tuning section
Co-authored-by: Matthew Barrett <matthew.barrett@arm.com>
Co-authored-by: Tristan Konolige <tristan.konolige@gmail.com>
Co-authored-by: Cody Yu <comaniac0422@gmail.com>
Leandro Nunes [Fri, 2 Oct 2020 02:25:56 +0000 (03:25 +0100)]
[tvmc] Introduce 'run' subcommand (part 4/4) (#6578)
* [tvmc] Introduce 'run' subcommand (part 4/4)
* Add 'tvmc run' subcommand to execute compiled modules
* Include options to locally or remotelly using RPC
* Include support to cpu and gpu devices
Co-authored-by: Marcus Shawcroft <marcus.shawcroft@arm.com>
Co-authored-by: Matthew Barrett <matthew.barrett@arm.com>
* adjust based on code review comments
* make test fixture to safely skip environments without tflite
* make --help option more clear
* improve error message to show expected inputs
* code-review adjusts
* update doc-string to default zeros->random
Co-authored-by: Marcus Shawcroft <marcus.shawcroft@arm.com>
Co-authored-by: Matthew Barrett <matthew.barrett@arm.com>
Andrew Reusch [Thu, 1 Oct 2020 16:48:35 +0000 (09:48 -0700)]
Add ci_qemu docker image (#6485)
* Add ci_qemu docker image
* build qemu from source
* add ubuntu1804 install script
* receive keys from keyserver
* pin to zephyr 2.3.0
* install 2.4.0
* add cache directory
* revert 3rdparty/vta-hw
Yizhi Liu [Thu, 1 Oct 2020 16:16:56 +0000 (09:16 -0700)]
[Doc] add KEYS to downloads.apache.org (#6581)
Leandro Nunes [Thu, 1 Oct 2020 16:16:36 +0000 (17:16 +0100)]
[docs] Missing documentation 'autodocsumm' (#6595)
lliu0 [Thu, 1 Oct 2020 16:15:54 +0000 (00:15 +0800)]
[Parser] Fix parsing op string attributes (#6605)
Co-authored-by: Lei Liu <lei.liu@streamcomputing.com>
Andrew Reusch [Thu, 1 Oct 2020 16:14:54 +0000 (09:14 -0700)]
add black-format to docker/lint.sh, suppport in-place format (#6601)
Josh Fromm [Thu, 1 Oct 2020 14:40:39 +0000 (07:40 -0700)]
Allow datatypes besides fp32 in conv2d_transpose for cuda. (#6593)
Zhi [Thu, 1 Oct 2020 07:46:56 +0000 (00:46 -0700)]
dynamic conv2d for cuda (#6598)
Andrew Reusch [Thu, 1 Oct 2020 02:50:42 +0000 (19:50 -0700)]
properly pass through command-line args in docker/bash.sh (#6599)
mbaret [Wed, 30 Sep 2020 17:32:32 +0000 (18:32 +0100)]
[BYOC][ETHOSN] Fix tests for new module API (#6560)
* [BYOC][ETHOSN] Fix tests for new module API
Some of the downstream variants of our tests had
been broken by a recent change to the API of build.
This both fixes that and refactors a couple of tests
so that they will run entirely in upstream CI and
we won't see this sort of failure again.
Change-Id: I841266eef0e2e89cc76e0526fc6cd3fc8d1326d8
* Only run mobilenet
Change-Id: Ie41c6d2c13c4473ecaa5c50c33d2c1589c742796
* Improve docs
Change-Id: I2c8bde44278e4cbc9cea5c5cbd4bb3c316ec37ae
* More docs
Change-Id: Ia9973915eecea647689535cc1e6eef9228111324
Tianqi Chen [Tue, 29 Sep 2020 20:40:41 +0000 (13:40 -0700)]
[RUNTIME] NDArray CopyFrom/To Bytes always synchronize (#6586)
* [RUNTIME] NDArray CopyFrom/To Bytes always synchronize
The previous behavior of non-sync can be unsafe for GPU devices.
In particular, the need for an explicit synchronization could
leads to confusion behavior e.g. asnumpy does not immediately return
the right content for vulkan.
Also brings the requirement of array being contiguous.
Right now we encourage compact array since they are easier for optimization.
We can consider bring support later by introducing a compactify PackedFunc(which might need be jitted).
Leandro Nunes [Tue, 29 Sep 2020 16:40:46 +0000 (17:40 +0100)]
[tvmc] Introduce 'tune' subcommand (part 3/4) (#6537)
* tvmc: introduce 'tune' subcommand (part 3/4)
* introduces a subcommand to drive auto-tuning
Co-authored-by: Matthew Barrett <matthew.barrett@arm.com>
Co-authored-by: Luke Hutton <luke.hutton@arm.com>
Co-authored-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
* [tvmc] address code review comments
* adjust --min-repeat-ms default value logic
* re-arrange rpc arguments to be --rpc-tracker=hostname:port and --rpc-key=str
* use a local reference of the tvmc logger
* add --target-host, default to llvm
Co-authored-by: Matthew Barrett <matthew.barrett@arm.com>
Co-authored-by: Luke Hutton <luke.hutton@arm.com>
Co-authored-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
masahi [Tue, 29 Sep 2020 10:00:14 +0000 (19:00 +0900)]
disable stacked bidir test (#6585)
Co-authored-by: masa <masa@pop-os.localdomain>
Chris Sullivan [Tue, 29 Sep 2020 09:59:54 +0000 (02:59 -0700)]
Add rocblas_sgemm_strided_batched impl. (#6579)
Yizhi Liu [Tue, 29 Sep 2020 08:05:05 +0000 (01:05 -0700)]
[COMMUNITY] vegaluisjose -> Committer (#6582)
Leandro Nunes [Tue, 29 Sep 2020 05:15:36 +0000 (06:15 +0100)]
[tvmc] unify all logs on a single logger 'TVMC' (#6577)
Yizhi Liu [Mon, 28 Sep 2020 17:41:09 +0000 (10:41 -0700)]
[Doc] Update release document (#6573)
Trevor Morris [Mon, 28 Sep 2020 17:35:01 +0000 (10:35 -0700)]
Support mxnet dot and LogisticRegressionOutput (#6542)
Leandro Nunes [Mon, 28 Sep 2020 16:50:00 +0000 (17:50 +0100)]
[tvmc] Fix command line argument variable name (#6574)
* This is a variable that we changed names during code review,
and it was incorrectly left behind with the previous name.
eric [Mon, 28 Sep 2020 15:26:56 +0000 (00:26 +0900)]
Fix android runtime error (#6575)
codes for USE_RANDOM in tvm4j was missing.
isong [Mon, 28 Sep 2020 04:24:10 +0000 (21:24 -0700)]
Fix missing te in the code example (#6569)
- caused `AttributeError: module ‘tvm’ has no attribute ‘thread_axis’
error
- Fix baesd on https://discuss.tvm.apache.org/t/attributeerror-module-tvm-has-no-attribute-thread-axis/6606
Tianqi Chen [Sun, 27 Sep 2020 22:30:25 +0000 (15:30 -0700)]
[TEST] Temporary disable test_mutate_parallel (#6572)
* [TEST] Temporary disable test_mutate_parallel
* Use skip
Lianmin Zheng [Sun, 27 Sep 2020 09:18:10 +0000 (02:18 -0700)]
[AutoScheduler] Improve the rule of mutating parallel granularity (#6568)
* fix mutate parallel
* fix comments
* fix lint
* fix tutorials
* update
* fix tests
* address comments
Andrew Liu [Sun, 27 Sep 2020 09:17:39 +0000 (02:17 -0700)]
[BYODT] fix CMAKE flag name + update documentation (#6567)
* documentation fixes + better name
* fix up comments
dlexplorer [Sun, 27 Sep 2020 00:01:01 +0000 (03:01 +0300)]
[APP] Fix misprint in demo.cc during initializing of picture tensor data (#6566)
Gus Smith [Sat, 26 Sep 2020 22:49:20 +0000 (15:49 -0700)]
Bring Your Own Datatypes (#5812)
* Add ChangeDatatype pass and unittest
* [WIP] Jared's work on Fri
This was work that Jared did on my computer, trying to get Inception v3 running.
* Fix simplify inference to work over different data types.
* Formatting
* Copy setup code from other test file
* Logging in Relay
* Remove duplicate TVM_DLL
* Add Sub, Mul, Div, Max to bfloat lib
* Fix previous broken rebased commit
* Remove line
* Add LowerCustomDatatypes to build passes
* Upcast ints to custom datatypes too, as well as to floats
* Add and use convert_ndarray
* Lower Call
* Relay: create constant scalars of custom dtypes
We use the same method we use in TVM: store the value in a double.
* Custom datatype formatting in Relay
* Update unittests
* Add simpler example that's not working yet
* Add Python unittests to Makefile
* Fix bug
* Fix function name in GetPackedFunc call
* convert_ndarray makes its own executor
* Add simple test case
* Move setup() calls
* Use convert_ndarray
* Change import to make it more specific
* Fix another Registry::Get call
* Allow users to register minimum functions for custom datatypes
This commit allows users to register global functions named
`tvm.datatype.min.<type name>` which take the number of bits in the custom type
and return the corresponding minimum value (as a double).
A similar commit will need to be created for max, whenever that ends up being
needed!
* Remove check for float
* Add test
* Fix inception test
* Add MobileNet
* Lower custom datatypes before intrinsics
* Add exp and sqrt bfloat functions
* [buggy commit] Lower intrinsics like sqrt, exp
This commit has bugs in it, I'm fairly certain.
* Formatting
* Fix bug
* Add lowering for new ops in test
* Add int to bfloat
* Remove print
* Add all tests
* Correct image size
* Add TODO
* Add "notbfloat" type
This type is for testing purposes. It just stores a float in a uint32. It was
used to confirm the fact that my bfloat "implementation" is very numerically
unstable and was causing issues when running the model.
* Convert arguments
Not sure how necessary this actually is.
* Rewrite custom datatype constants in Relay
* Add test_ops
* Print constants in Relay
* Use topi.testing
* Test conv2d
* Add test_model
* Comment out model tests
* Register notbfloat
This could be unregistered at some point later
* Add commented code
Remove later
* Add posit tests
* test_ops_same_function
* [temporary] move incomplete commit to macbook
* Add more to tests
* Formatting
* Uncomment add
* Remove bad tests
* Change comments
* Change function name and docstring
* Change main function
* Restructure tests
* Fix visibility of posit functions
* YAPF
* Switching keywords around to resolve build errors on some systems
* Improve test by running smaller mobilenet
* Add test_cast
* Change datatype name; add simple test
* Rename to posit32
* Merge 3 posit types into one file
* Add a nop type
* Remove bfloat
* Refactor test comments
* Refactor conv2d test
* Add optional tolerance arguments
* Add posit8 and posit16
* Add comment about posit8
* Whoops -- actually add noptype to CMakeLists
* Add rtol, atol to run_workload
* Add noptype to tests
* Run noptype over other models, too
* Pass correct arguments to calls
* Fix line length errors
* Raise tolerances (again) to avoid flaky test
* fix style
* add test for tanh, log, sigmoid
* Remove references to bfloat, notbfloat
* Change comments
* Remove old test file
* fix min func
* refactoring unit test file
* use posits es2
* cleanup
* comment
* coment if_then_else
* support different bit widths
* use random seed to create stable tests
* update documentation
* removed nop-type and code consistency
* add batchnorm test
* rebase and update
* fix tests and format
* pylint
* change order of include
* include order
* fix style
* remove posit c linkage
* update universal
* fix style
* fix test
* fix overflow error with minfunc and posits
* style
* use change_dtype to convert params
* update universal
* fix fatal error
* fix constant repr
* minor update to posites2
* update universal
* fix rst
* fix invalid import and sqrt
* update universal
* comments
* comments and expand testing
* increase atol/rtol for custom[posites2]32
* Re-add newline
* Remove comment
* Remove opt level and comment
* Change docstring
* Add TODO
* Add file header and newline
* Update docstring
* Update file docstring
* Update docstrings
* Delete todos
* create_min_lower_func
* add better debugging message
* docs
* add BYODT tutorial
* add todo
* Reformat some of tutorial to RST, plus code fixes
* tutorial notebook runs now
* fix hyperlink
* rebase
* add to tutorial
* fix mobilenet model
* add skip tag
* black lint
* add compiler flag and add dummy float
* myfloat and posites2 test
* remove universal
* lint
* lint
* add setup
* build with USE_POSIT for CI/CD
* fix posit cmake
* add cd /
* undo docker changes
* change tutorial to use myfloat
* move files
* lint
* fix
* remove filter
* fix lint
* fix suggestions
Co-authored-by: Jared Roesch <roeschinc@gmail.com>
Co-authored-by: Andrew Liu <andrewlliu@gmail.com>
Tristan Konolige [Sat, 26 Sep 2020 22:32:08 +0000 (15:32 -0700)]
Rename tvm.hybrid.script to tvm.script. (#6522)
Cody Yu [Sat, 26 Sep 2020 16:22:16 +0000 (09:22 -0700)]
Make CMakefile/config.cmake/install_tvm consistent (#6562)
Zhi [Sat, 26 Sep 2020 03:29:40 +0000 (20:29 -0700)]
Zhi's key for ASF release (#6554)
Balint Cristian [Fri, 25 Sep 2020 16:37:20 +0000 (19:37 +0300)]
Add proper cmake PATHS when multiple NAMES. (#6558)
Chenfan [Fri, 25 Sep 2020 16:36:43 +0000 (00:36 +0800)]
[Ansor][FLAKY] Bug fix for compute at mutation error (#6557)
Trevor Morris [Fri, 25 Sep 2020 15:39:08 +0000 (08:39 -0700)]
Make missing desired layout non-fatal (#6553)
lixiaoquan [Fri, 25 Sep 2020 14:37:56 +0000 (22:37 +0800)]
[TIR] Fix rewrite_simplify tir::builtin::shift_left (#6555)
Liu Qi [Fri, 25 Sep 2020 14:04:30 +0000 (22:04 +0800)]
Feat(frontend-pytorch): Add input types argument and Support cast to float16. (#6546)
1. Add input types argument for converting TorchScript file.
2. Support casting float32 to float16 when converting to operation.
ziheng [Fri, 25 Sep 2020 09:01:42 +0000 (02:01 -0700)]
[COMMUNITY] Add Ziheng's key for ASF release (#6552)
Robert Kimball [Fri, 25 Sep 2020 05:08:12 +0000 (22:08 -0700)]
Generalize the use of booleans to support all cmake boolean values. (#6515)
* Generalize the use of booleans to support all cmake boolean valuues.
* Update to use a more simple method to detect if variable is a false value
* Fix some errors
* Debug CI issue
* Fix logic error in cmake changes
* Use new IS_TRUE_PATTERN to make intent clear
Rishabh Jain [Fri, 25 Sep 2020 04:06:15 +0000 (09:36 +0530)]
[Relay/TOPI] Added dilation_value attribute to dilate operator. (#6550)
* Added dilation_value attribute to dilate operator of Relay/TOPI.
(Enables custom value for dilation, instead of always 0)
* Added tests for dilation_value of dilate operator in Relay and TOPI.
Josh Fromm [Fri, 25 Sep 2020 00:47:36 +0000 (17:47 -0700)]
[Frontend][Onnx] Added broadcasting to prelu alpha. (#6549)
WenheLI [Fri, 25 Sep 2020 00:46:43 +0000 (19:46 -0500)]
update webgpu api (#6547)
韩朴宇 [Thu, 24 Sep 2020 15:50:49 +0000 (23:50 +0800)]
[Rust] Allow convert Context to ArgValue (#6544)
Robert Kimball [Thu, 24 Sep 2020 15:50:08 +0000 (08:50 -0700)]
Add alternate cublaslt library name. CUDA 11.0 uses cublasLt. (#6541)
Rishabh Jain [Thu, 24 Sep 2020 15:43:28 +0000 (21:13 +0530)]
[Relay/TOPI] Added 'offsets' and 'alignment' attributes to MATRIX_SET_DIAG. (#6429)
* [Relay/TOPI] Added 'offsets' and 'alignment' attributes to MATRIX_SET_DIAG.
* Added support for 'offsets' and 'alignment' attributes of MATRIX_SET_DIAG.
(Similar to MATRIX_SET_DIAG V3 of TF)
* Added tests for 'offsets' and 'alignment' attributes of MATRIX_SET_DIAG.
* Changes by black.
* * Added offset check in Relay.
* Minor changes.
* Added more tests and some minor documentation changes.
Leandro Nunes [Thu, 24 Sep 2020 06:48:10 +0000 (07:48 +0100)]
tvmc: solve a linting error on onnx command line driver frontend (#6536)
* Updates onnx load function from "load" (a compatibility attribute)
to "load_model" (the actual function)
* Add a pylint command, that we don't see currently on upstream CI,
but it reproduces when linting it locally.
Leandro Nunes [Wed, 23 Sep 2020 20:02:56 +0000 (21:02 +0100)]
Remove unused pylint 1.9.4 from docker installation script (#6538)
Hua Jiang [Wed, 23 Sep 2020 16:54:05 +0000 (09:54 -0700)]
[Relay] Show yolo detection result in text. (#6367)
* [Relay] Show yolo detection result in text.
Issue:
Current yolo detection only provide a image drawing solution
to output detection result, but for console user, such result
would not available for a view.
Solution:
Here we add a text show function to show detection result in
text format for testing in console scenario.
* rebase upstream and merge code change.
* address review comments.
Giuseppe Rossini [Wed, 23 Sep 2020 16:42:24 +0000 (17:42 +0100)]
[BYOC][ACL] Add maximum support for float32 (#6506)
* ACL integration: add maximum support for float32.
* Added the code generation flow in arm_compute_lib.py
* Added the runtime calls in acl_runtime.cc
Change-Id: I69c5522f05a46c1dd235da5d57fe499134de0425
* Add maximum to the list of supported functions
Change-Id: Ia49087756be4c3ac92a3dc76fe03fb00de468f8d
Chenfan [Wed, 23 Sep 2020 15:37:42 +0000 (23:37 +0800)]
[Ansor] Parallel the InitPopulation (#6529)
Shuwei Liu [Wed, 23 Sep 2020 15:20:23 +0000 (23:20 +0800)]
[FIX] fix the python script for building resnet (#6526) (#6527)
Qiang Zhang [Wed, 23 Sep 2020 15:18:40 +0000 (23:18 +0800)]
[TUTORIAL] Fix Some Failed Tutorials of The Issue #6453 (#6534)
Robert Kimball [Wed, 23 Sep 2020 02:44:26 +0000 (19:44 -0700)]
Add the SYSTEM keyword to all cmake include_directories commands for 3rd party or external headers. Warning flags should only be applied to code within the tvm repository. (#6531)
Zihao Ye [Wed, 23 Sep 2020 02:40:07 +0000 (10:40 +0800)]
[Doc][Fix] Fix a typo in hybrid script tutorial. (#6525)
qixiuai [Tue, 22 Sep 2020 17:07:48 +0000 (01:07 +0800)]
Remove settings about SGX in config.cmake (#6530)
removed settings about SGX since SGX is removed from TVM core
Robert Kimball [Tue, 22 Sep 2020 14:47:34 +0000 (07:47 -0700)]
[DOCS] Change some tutorial text (#6514)
Andrew Reusch [Tue, 22 Sep 2020 14:36:05 +0000 (07:36 -0700)]
fix libtvm build dependencies when USE_MICRO is ON. (#6524)
* previously, building from scratch would fail with Unix Makefiles
due to cmake limitation
masahi [Tue, 22 Sep 2020 02:59:00 +0000 (11:59 +0900)]
[Torch] Clean up usage of try ... infer_value() ... except (#6504)
* clean up infer value usage
* try silence pylint
* remove unused variable
* make on_failuare optional
* make on_success optional True
Co-authored-by: masa <masa@pop-os.localdomain>
Thierry Moreau [Tue, 22 Sep 2020 01:32:25 +0000 (18:32 -0700)]
[TOPI] Group conv2d NHWC op implementation (#6510)
Robert Kimball [Tue, 22 Sep 2020 01:18:02 +0000 (18:18 -0700)]
Enable more warnings when compiling with clang 10.0 or greater (#6456)
Lianmin Zheng [Tue, 22 Sep 2020 00:46:52 +0000 (17:46 -0700)]
[AutoScheduler] Improve hyperlinks in the tutorial (#6521)
* improve auto-scheduler tutorials
* improve tutorials
* fix lint
Tianqi Chen [Mon, 21 Sep 2020 15:46:41 +0000 (08:46 -0700)]
[LINT] Use fmt off to disable problematic black fmt (#6519)
Dmitriy Smirnov [Mon, 21 Sep 2020 09:22:59 +0000 (10:22 +0100)]
QnnBinaryLayout bugfix + unit test (#6513)
An attempt to fix an issue which appeared when ConverLayout pass
runs on quantized binary operations like qnn.add:
def before():
x = relay.var("x", shape=(2, 2))
y = relay.var("y", shape=(1, 2))
return relay.Function(
[x, y],
relay.qnn.op.add(
x,
y,
lhs_scale=relay.const(0.0156863, "float32"),
lhs_zero_point=relay.const(127, "int32"),
rhs_scale=relay.const(0.0117647, "float32"),
rhs_zero_point=relay.const(85, "int32"),
output_scale=relay.const(0.0235294, "float32"),
output_zero_point=relay.const(128, "int32"),
),
)
The issue manifested itself as
[bt] (2) ./src/tvm/build/libtvm.so(tvm::relay::qnn::QnnBinaryBroadcastLayout(tvm::Attrs const&, tvm::runtime::Array<tvm::tir::Layout, void> const&, tvm::runtime::Array<tvm::tir::Layout, void> const&, tvm::runtime::Array<tvm::Type, void> const&)+0xa9) [0x7fadc080d949]
[bt] (1) ./src/tvm/build/libtvm.so(tvm::runtime::Array<tvm::tir::Layout, void>::operator[](long) const+0xb6) [0x7fadc0382996]
[bt] (0) ./src/tvm/build/libtvm.so(+0xb50c12) [0x7fadc037cc12]
File "/workspace/include/tvm/runtime/container.h", line 681
IndexError: Check failed: 0 <= i && i < p->size_: indexing 1 on an array of size 1
Tianqi Chen [Mon, 21 Sep 2020 00:49:23 +0000 (17:49 -0700)]
[CI] Cancel previous build if new commit has been pushed to a PR (#6518)
Xiao Xia [Sun, 20 Sep 2020 19:53:26 +0000 (03:53 +0800)]
[TOPI] Fix declaration_conv2d_transpose_impl (#6428)
Tianqi Chen [Sat, 19 Sep 2020 22:41:38 +0000 (15:41 -0700)]
Update CI badge location (#6517)
Lianmin Zheng [Sat, 19 Sep 2020 22:38:29 +0000 (15:38 -0700)]
[ANSOR] Auto-scheduler tutorial for GPU and necessary refactor/fix (#6512)
* add gpu tutorial
* refactor mutation in evolutionary search
* update
* update double matmul
* fix lint
* add double matmul test
* fix mutate compute location
* fix sketch search policy
* fix lint
* update
* address comments
* fix PruneInvalidStates
Leandro Nunes [Fri, 18 Sep 2020 18:37:13 +0000 (19:37 +0100)]
[tvmc] command line driver 'compile' (part 2/4) (#6302)
* [tvmc] command line driver 'compile' (part 2/4)
* Add 'compile' subcommand into tvmc (tvm.driver.tvmc)
* Add frontends: Keras, ONNX, TensorFlow, tflite, PyTorch
* Add tests for the 'compile' subcommand
* Enable command line driver tests as part of integration tests
* Skip tests if the cross-compilation toolchain is not installed
Co-authored-by: Marcus Shawcroft <marcus.shawcroft@arm.com>
Co-authored-by: Matthew Barrett <Matthew.Barrett@arm.com>
Co-authored-by: Dmitriy Smirnov <dmitriy.smirnov@arm.com>
Co-authored-by: Luke Hutton <luke.hutton@arm.com>
Co-authored-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Co-authored-by: Matthew Barrett <matthew.barrett@arm.com>
Co-authored-by: Elen Kalda <elen.kalda@arm.com>
Co-authored-by: Ramana Radhakrishnan <ramana.radhakrishnan@arm.com>
Co-authored-by: Jeremy Johnson <jeremy.johnson@arm.com>
Co-authored-by: Ina Dobreva <Ina.Dobreva@arm.com>
* tvmc: adjust TODOs
* tvmc: fix linting errors
* Address code-review comments
* Adjust pytest fixture to not break when there is no tensorflow
* Fix frontend tests, to cope with different frameworks in different images
* Apply suggestions from code review
Co-authored-by: Cody Yu <comaniac0422@gmail.com>
* Fix lint and code-review issues
* Re-format with black.
* tvmc: Move dependencies to extras_requires
Co-authored-by: Marcus Shawcroft <marcus.shawcroft@arm.com>
Co-authored-by: Matthew Barrett <Matthew.Barrett@arm.com>
Co-authored-by: Dmitriy Smirnov <dmitriy.smirnov@arm.com>
Co-authored-by: Luke Hutton <luke.hutton@arm.com>
Co-authored-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Co-authored-by: Elen Kalda <elen.kalda@arm.com>
Co-authored-by: Ramana Radhakrishnan <ramana.radhakrishnan@arm.com>
Co-authored-by: Jeremy Johnson <jeremy.johnson@arm.com>
Co-authored-by: Ina Dobreva <Ina.Dobreva@arm.com>
Co-authored-by: Cody Yu <comaniac0422@gmail.com>
Honghua Cao [Fri, 18 Sep 2020 17:29:12 +0000 (01:29 +0800)]
[RELAY][OP] roi_align operator alter layout (#6443)
* [RELAY][OP] roi_align operator alter layout
* [RELAY][OP] roi_align operator alter layout
* [RELAY][OP] roi_align operator alter layout
* [RELAY][OP] roi_align operator alter layout
Co-authored-by: honghua.cao <honghua.cao@streamcomputing.com>
Tom Gall [Fri, 18 Sep 2020 15:41:55 +0000 (10:41 -0500)]
Add beagleboard ai, thunderx and stm32mp1 to the arm_cpu target. (#6501)
* Add beagleboard ai, thunderx and stm32mp1 to the arm_cpu target.
Signed-off-by: Tom Gall <tom.gall@linaro.org>
* updates from black on target.py
Signed-off-by: Tom Gall <tom.gall@linaro.org>
Yao Wang [Fri, 18 Sep 2020 15:39:47 +0000 (08:39 -0700)]
[Relay]Allow dynamic batch for arm conv2d (#6509)
* Allow dynamic batch for arm conv2d
* Add TODO
Yong Wu [Fri, 18 Sep 2020 10:16:27 +0000 (18:16 +0800)]
Add several op mapping in PyTorch frontend (#6472)
* Add copy_ and clamp_ in PyTorch frontend
* add true_divide in PyTorch frontend
* more test cases for copy_
* fix format
* remove copy_
* fix format
* skip true_divide for torch < 1.5
Yizhi Liu [Fri, 18 Sep 2020 08:34:40 +0000 (01:34 -0700)]
[COMMUNITY] hypercubestart -> Reviewer (#6511)
Shizhi Tang [Fri, 18 Sep 2020 05:30:22 +0000 (13:30 +0800)]
improve doc for relay.nn.dense (#6508)
lhutton1 [Thu, 17 Sep 2020 21:49:32 +0000 (22:49 +0100)]
[RPC] Lazily import micro when starting an RPC server (#6505)
* [RPC] Lazily import micro when starting an RPC server
Since #6334 the RPC server cannot be started unless USE_MICRO is enabled. I've tracked this down to an import in `python/tvn/exec/rpc_server.py`: `from tvm import micro` in the top level list of imports. This will mean that we try to import micro when it's not been built. Fix this by lazily importing micro when initializing an rpc server with micro enabled.
Change-Id: I8f22d81e215cfe4ac0662b0a99bdf02a3e91f90c
* fix lint
Change-Id: I8b78b678374bc82b3b66a7b3595ed4f1684e7d90
Bohan Hou [Thu, 17 Sep 2020 21:49:09 +0000 (05:49 +0800)]
[TIR][Hybrid] Hybrid Script Improvement (#6507)
* [TIR][Hybrid] update
* [TIR][Hybrid] python formatting
Andrew Reusch [Thu, 17 Sep 2020 14:59:39 +0000 (07:59 -0700)]
Switch CRC-CCITT libraries (#6499)
Yao Wang [Thu, 17 Sep 2020 10:08:52 +0000 (03:08 -0700)]
Add PT OD tutorial (#6500)
Shizhi Tang [Thu, 17 Sep 2020 10:08:13 +0000 (18:08 +0800)]
fix a typo in topi key (#6502)
Yao Wang [Thu, 17 Sep 2020 03:32:20 +0000 (20:32 -0700)]
[Frontend][Pytorch] Improve Pytorch frontend for object detection models (#6449)
* Improve Pytorch Frontend
* Add tests
* Fix pylint
* Improve data cast
* Use int64 for slice axis
* Fix lint
* fix roi_align(..., aligned=True)
* Minor fix
* Add e2e test
* Add asf header
* Minor change
* Use dynamic topk
* Improve test
* Rollback topk
* py format
* remove print
* More improve
* Fix test
* Improve addmm
* Fix test
* Fix format
* Fix format
* Fix test scatter
Co-authored-by: q.yao <streetyao@live.com>
Lianmin Zheng [Thu, 17 Sep 2020 02:14:09 +0000 (19:14 -0700)]
[TUTORIAL][ANSOR] Using the template-free auto-scheduler on CPU (#6488)
* add tutorial
* add tutorial
* update
* Apply suggestions from code review
Co-authored-by: Cody Yu <comaniac0422@gmail.com>
* address comments
* fix bugs
* add the exmple for resuming the search
* fix lint
Co-authored-by: Cody Yu <comaniac0422@gmail.com>
Thierry Moreau [Thu, 17 Sep 2020 01:11:55 +0000 (18:11 -0700)]
extending FindVulkan to build RPC server on Windows correctly (#6498)
Co-authored-by: Mei Ye <meiandmimi@yahoo.com>
Co-authored-by: Mei Ye <meiandmimi@yahoo.com>
Tianqi Chen [Wed, 16 Sep 2020 23:19:52 +0000 (16:19 -0700)]
[BUILD] enhance build script for optional vta dep (#6497)
Matthew Brookhart [Wed, 16 Sep 2020 22:37:36 +0000 (16:37 -0600)]
black format master (#6494)
Thierry Moreau [Wed, 16 Sep 2020 20:25:08 +0000 (13:25 -0700)]
bumping vta version (#6495)