Age | Commit message (Collapse) | Author |
|
* Add automatic tag handling when building source distribution.
Change-Id: Ia20df463ae3eddf78de7e0b710c9c2279ddf61cd
Signed-off-by: Raul Farkas <raul.farkas@arm.com>
|
|
- Updated release notes for 3.7.0
- Updated tag in SUPPORTED_OPS and setup.py
- Tidied up README
Change-Id: Ib33a3d85383ce297b10acd74f8a2455d738276be
Signed-off-by: Tim Hall <tim.hall@arm.com>
|
|
- Move all static information from setup.py to newly added
pyproject.toml
- Add setup.cfg used for static information that cannot be added to
pyproject.toml due to it still being in beta.
- Modify mlw_codec to to throw a real python exception when importing
NumPy arrays instead of just printing them to stdout.
- Surround mlw_codec import with try catch statement to catch NumPy C
API mismatch errors and throw them again with a more detailed message.
- Update README.md with documentation about known issue with changing
used NumPy version after installing ethos-u-vela.
Change-Id: I1eeee5536be7c1744e30d6088f7069fbb1403e06
Signed-off-by: Raul Farkas <raul.farkas@arm.com>
|
|
- Update SUPPORTED_OPS.md with release version
- Update setup.py with release version
- Update RELEASES.md with release notes and comments
Change-Id: If5cd5525d8a52a13245940bfbb262db8c9e13003
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
|
|
- Update copyright notices to use SPDX format and add OSS mail as contact.
- Update years on files where it had been missed.
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
Change-Id: I7e9715ea4e17b76252728c708e46df12ad67ab1f
|
|
- The issue is due to the numpy version needed when installing on
aarch64 with Python 3.8 and TensorFlow
- The fix is to use the python_version variable when specifing the
numpy version
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I6134b6dbccefc3be0b87feb17e3176b7f42641b3
|
|
- Updated to TensorFlow 2.10 and FlatBuffers 2.0.7
- Changed absolute to relative imports in the auto-generated code
- Updated Vela's TFLite writer to support FlatBuffer builder's internal
number of elements count
- Removed use of deprecated numElems argument to FlatBuffer builder's
EndVector()
Signed-off-by: erik.andersson@arm.com <erik.andersson@arm.com>
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: If447778134db81ae0ac374c7397e1140082372fd
|
|
- Updated SUPPORT_OPERATORS.md with Resize operators
- Updated release notes with the main changes and bug fixes
- Updated version numbers
Signed-off-by: oliper01 <oliver.perssonbogdanovski@arm.com>
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: If25b5fab708098bc3e7eb243924b55a50f148c3a
|
|
There is an issue with using NumPy 1.21.4 or above in setup.py with
python 3.7. Restriction can most likely be removed when upgrading to
python 3.8.
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
Change-Id: I9f826201d68bb5ab61f5bf76c7796442d34447b9
|
|
- Updated release notes and setup.py tag for 3.4
- Regenerated supported ops information
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I4ec88544b84cab168cb3e5cbc6bc392b6b3d8a39
|
|
- The latest numpy versions require Python 3.8
- This can cause issues if Python 3.7 is installed which is the version that
Vela is tested against
- The fix is to limit the numpy version to those that support Python 3.7
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I3a388976d5aa76395ca93202e496640c8de9f6f4
|
|
Add directory structure to support third party config files. Config
files should now be placed in an appropriately named directory under
the config_files directory, but can also be accessed by providing its
absolute path to vela --config.
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
Change-Id: I2fcf52e7b2ddd2c4491dc370c85c0b3937d18062
|
|
This commit downgrades the required Python version
to 3.7 from 3.8.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I07057908b97bcd94663f001474d877ba41411ae1
|
|
Removed numpy version limit.
Change-Id: I01e4d27754fe037be227d7329c4e1a8f1cea6315
Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com>
|
|
Add mypy to pre-commit and clean up all reported errors.
Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com>
Change-Id: If7dc869f5fecdb0e2db40f14e7d9db21aa33df71
|
|
- Bump minor release version and add release notes
- Update README and SUPPORTED_OPS versions
Change-Id: Ic14d028483c12d281e69515b25f66346d9a3afeb
Signed-off-by: James Peet <james.peet@arm.com>
Signed-off-by: Tim Hall <tim.hall@arm.com>
|
|
Change required python version from 3.6 to 3.8 in setup.py and allow
any python3 version for black pre-commit linting.
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
Change-Id: I0d8936d92efd5137561834c0de1a3449f9e5f25c
|
|
This reverts commit 3c25ff658cf847ccfcb2d4d5796ffbe13a511894.
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I5403bf4c53dced1075160313876fa8681eaa617f
|
|
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com>
Change-Id: I288decbc0affa7f9475cabbd16cd20005e15e2a2
|
|
This commit updates the release notes for Vela
version 3.2.0.
It also updates the SUPPORTED_OPS.md file with new
constraints.
Updated the API version as a result of the bug fix
commit 399c4a2d77df791e5d988c51d7fb1824ac4f266f.
Updated Vela version in setup.py.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I181e89f639a1da6013e8511ebe2d7e4f81242916
|
|
This commit adds the author_email field with email
address <mlg-vela@arm.com> to the
setuptools.setup() function in setup.py.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: If3b2605ea9b05a8a4c6f899d8af77cbaec9ce9b5
|
|
This commit contains the release notes
for Vela 3.1.0. It also increases the
PyPI documentation tag.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: Iffd9fac7d4a7ccb34c3558990ef4bb97e548bf4c
|
|
To avoid using Python 3.6 incompatible versions of NumPy (> 1.19.5),
an upper bound on version is added for NumPy in setup.py.
Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com>
Change-Id: I3929bd7dbea6866905665186af1c4b3ba43ccbd0
|
|
Adds tosa package to setup.py
Change-Id: I931301313b6d79402e3caf53df7718588a5f538d
Signed-off-by: James Peet <james.peet@arm.com>
|
|
Removed:
Programming Language :: Python :: 3.6 :: Only
As it is not a valid classifier
Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com>
Change-Id: Iebd1afa19952d7b90f4ddacf2ec5bf15252b9354
|
|
- Changed the tag to 3.0.0
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I309fcaa76c6595ca08c39b27a0fc3cf58b40dd52
|
|
Fixed sub-module imports.
Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com>
Change-Id: I6ab5c04ba5f3411f8cf8ac95606fe036fae11442
|
|
This commit removes usage of the function
find_namespace_packages (which is not available in
older versions of setuptools) and instead explicitly
states the namespace packages in setup.py.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I942f339953d50a7bf5fc3e83c0736813fea58dd2
|
|
This commit changes setup.py to correctly
state that we only officially support Python 3.6.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: Iaa678d1df6a154fdb24f3b3994015a3e842d7696
|
|
This commit fixes a potential end user problem where
the user needs NumPy installed in order to run setup.py.
This creates a situation where if the user needs to
manually install NumPy in order to install Vela.
This solution moves the NumPy dependent code into the
setup process and allows it to be installed as a
dependency first.
Signed-off-by: Dwight Lidman <dwight.lidman@arm.com>
Change-Id: I5d7d3d30c3755e8f7c369df8d34738f5c53877dd
|
|
Fixedx size calculation in mlw_reorder_encode.
Fixed build warnings.
Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com>
Change-Id: Iac9408b9972a29b5a3403ba11f80dc4eaaa35453
|
|
- Moves reordering to C
- Runtime is greatly minimized for encoding weights
Change-Id: Ifff01e7b1ea6d5cec68310a155c3b80aa1a38545
Signed-off-by: Mauricio Briceno <mauricio.briceno@arm.com>
|
|
- Updated tag to 2.1.1
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I2c35557058421d2be5c934e2a1cb06a5718b4697
|
|
- Updated release notes
- Updated supported ops
- Clarified platform support
- Minor clean up of README
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I62b9ff66fc7729b184a5dbb322406cfcdef4e542
|
|
- Straight port of the C++ implementation to python.
- Renamed the allocator from "Search" to "HillClimb"
Change-Id: I50797d541f326d0264daf79bf7866aef32350a60
Signed-off-by: Louis Verhaard <louis.verhaard@arm.com>
|
|
Updated tflite loader and mappings from tensorflow 2.3 to tensorflow 2.4
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I55884000ee139baf639bb0377008e0534f72fe94
|
|
Updated setup.py with Microsoft Windows support.
Change-Id: I8cb042002c5530601e7ce2b3c99d40342886c3a9
Signed-off-by: Fredrik Svedberg <Fredrik.Svedberg@arm.com>
|
|
Various updates to make vela run and produce identical output on
Microsoft Windows.
* Fixed overflow errors
* Fixed compile warnings
* Avoid problematic numpy version
* Updated README.md
Signed-off-by: Fredrik Svedberg <Fredrik.Svedberg@arm.com>
Change-Id: Ie48c63a92a00c81b3247d07f05b75d881319ddbb
|
|
Added a new tensor allocator that is based on searching,
implemented in C++ (C++11 compatible).
Change-Id: Ie96e9fcfc8e6c58d1fa53911f37de290eeba88cf
Signed-off-by: Louis Verhaard <louis.verhaard@arm.com>
|
|
Replace exact instances, not just any occurance
Add ability to dump modified contents to a file "PYPI.md" to verify
changes are as expected.
To enable that mode, an environment variable is required to exist when
running pip or setup.py. e.g:
ETHOSU_VELA_DEBUG=1 pip install -e .
Signed-off-by: Michael McGeagh <michael.mcgeagh@arm.com>
Change-Id: Ia95530f38d5d78433c2d0e7c42bfff9532114285
|
|
Instead of just detecting MD files, detect any local files by checking
if they exist
Signed-off-by: Michael McGeagh <michael.mcgeagh@arm.com>
Change-Id: I02bd790b5bb148abfe16e4bdb3e38e68750cfb94
|
|
Instead of maintaining two almost identical readme files, have setup.py
read in the canonical README.md and modify it to replace the links
accordingly.
Signed-off-by: Michael McGeagh <michael.mcgeagh@arm.com>
Change-Id: Ia27cd48f3c945b3fac892ab1784ce394119968ac
|
|
- Tested and changed lxml to an older version
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: Ie097820008a4d60cb4549c659a90553a0ab9efa9
|
|
- Updated and aligned the --help and setup.py descriptions
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I78c11b1b3dd51284b34d57a6caca45cd222b4678
|
|
- Also changed to use Ethos-U where appropriate
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: Ie45ba2bb3935b305abe897b78b498681296cb7c1
|
|
- Added mechanism to track input to output graph transforms for
debugging the resultant command stream.
- Provides base implementation for MLBEDSW-2661
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I2dfe8a409fbde7ad0282bfab5acb11ba1c8b82d8
|
|
- Added release information
- Added PyPi documentation
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: Iaae64cfe10a2fa65f0559d13940b19d6f57edfdc
|
|
- Added PyPi installation info
- Added source code download/cloning info
- Updated development status in setup.py
Signed-off-by: Tim Hall <tim.hall@arm.com>
Change-Id: I5c2f7dfe19a222f008b5f825c58d0fec14792bc1
|
|
Also updated README.md
Change-Id: I118309c61f4d00e8508d6b888c606995490fba39
Signed-off-by: Diego Russo <diego.russo@arm.com>
|
|
- Added modules ethosu.vela and ethosu.mlw_codec.
- Added README and various configuration files.
Change-Id: I3690f8c8f5966306ecddaeb2793c30ca9c6e2eee
|