Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
ethos-u
/
ethos-u-vela
/
refs/tags/3.7.0
tag
24779d825c327bec8d9ecdab64c8c80bba8792a3
tagger
Rickard Bolin <rickard.bolin@arm.com>
Tue Feb 28 11:38:05 2023 +0100
object
c60b7e3a4cda84a196801baa407a0dcc5d39832b
23.02 Release.
« Previous
9b37918
MLBEDSW-4215: Add support for MEAN to match QuantizedMeanOrSum implementation
by Dwight Lidman
· 3 years, 4 months ago
c822d62
MLBEDSW-4223: Full support for PAD operator
by Louis Verhaard
· 3 years, 4 months ago
8ba0792
MLBEDSW-4070: Addresses errors with the LeakyReLU operator.
by erik.andersson@arm.com
· 3 years, 4 months ago
807278a
MLBEDSW-4209 Use live range alignment when allocating
by Henrik G Olsson
· 3 years, 4 months ago
41c006a
vela: Update release tag in setup.py
by Tim Hall
· 3 years, 4 months ago
2.1.1
7562bdf
MLBEDSW-4095: Update RELEASE notes and other docs
by Tim Hall
· 3 years, 4 months ago
2.1.0
2.1.0.rc3
4f728c0
MLBEDSW-1499: Add MEAN operator
by Dwight Lidman
· 3 years, 7 months ago
0cbb166
MLBEDSW-3571: Sum and FC should not crash when asking for keep_dims.
by erik.andersson@arm.com
· 3 years, 4 months ago
460c689
MLBEDSW-4064: Update copyright headers
by erik.andersson@arm.com
· 3 years, 4 months ago
b0b56d3
MLBEDSW-3938: Describe internal-default CLI value
by Tim Hall
· 3 years, 4 months ago
2.1.0.rc2
2b74b9a
MLBEDSW-4109: Add OPTIONS section to the README
by Tim Hall
· 3 years, 4 months ago
0fb3851
MLBEDSW-4110: Update Pipenv configuration files for TF2.4
by Tim Hall
· 3 years, 4 months ago
1a92f78
MLBEDSW-4022: support PAD followed by pool operator
by Louis Verhaard
· 3 years, 5 months ago
8d0f489
[MLBEDSW-3813] Fix LSTM operator pass through
by Fredrik Svedberg
· 3 years, 5 months ago
56b6c71
MLBEDSW-4076 Fix read_offset at create_primary_op
by Patrik Gustavsson
· 3 years, 5 months ago
ab11bd1
Make HillClimb allocation reproducible
by Fredrik Svedberg
· 3 years, 5 months ago
b70f817
Corrected the help string of --force-block-config
by Jacob Bohlin
· 3 years, 5 months ago
d700252
MLBEDSW-3808: Ported search allocator to python
by Louis Verhaard
· 3 years, 5 months ago
2.1.0.rc1
ad45f79
MLBEDSW-3509: Updated the debug database to support multiple custom operators.
by erik.andersson@arm.com
· 3 years, 5 months ago
42b94ed
MLBEDSW-3902: Fixes invalid op when cloning LeakyReLU operator
by erik.andersson@arm.com
· 3 years, 5 months ago
2a58530
MLBEDSW-3600: Cascading support for ResizeBilinear
by Jacob Bohlin
· 3 years, 5 months ago
2446e59
MLBEDSW-3774 Fix avoid cascading for spilling
by Patrik Gustavsson
· 3 years, 5 months ago
e3b1b91
MLBEDSW-3774 Remove SplitSliceRead
by Patrik Gustavsson
· 3 years, 5 months ago
138d47f
MLBEDSW-3774 Removed ConcatSliceWrite
by Patrik Gustavsson
· 3 years, 5 months ago
da2b003
MLBEDSW-3937 Fix check for NHCWB16 for FC
by Patrik Gustavsson
· 3 years, 5 months ago
455e20e
MLBEDSW-3953: Output diff in mobilenet_v3
by Diqing Zhong
· 3 years, 5 months ago
42abec1
MLBEDSW-3771: Updated to TF 2.4 flatbuffer schema
by Tim Hall
· 3 years, 5 months ago
73e843f
vela: Change Shape4D mutability usage
by Tim Hall
· 3 years, 5 months ago
133ba7e
MLBEDSW-3772 Removed fixup_act_reorder
by Patrik Gustavsson
· 3 years, 5 months ago
d1836c7
MLBEDSW-3937 Fix moving FM to fast storage
by Patrik Gustavsson
· 3 years, 5 months ago
3d22f3c
MLBEDSW-3932: Remove Squeeze from supported operators
by Louis Verhaard
· 3 years, 5 months ago
fcb1a00
MLBEDSW-3951 Consider reshaping in pass packing
by Patrik Gustavsson
· 3 years, 5 months ago
c776151
MLBEDSW-3572: Fused activations must not be int32
by Louis Verhaard
· 3 years, 5 months ago
66d7ec0
MLBEDSW-3927: Fix wrong compression ratio
by Diqing Zhong
· 3 years, 5 months ago
f2afd7f
[MLBEDSW-1743] Fix scaling for Abs operator
by Fredrik Svedberg
· 3 years, 5 months ago
ebf4af6
MLBEDSW-3903: Bug fix PAD operator
by Louis Verhaard
· 3 years, 5 months ago
189f748
MLBEDSW-3224: Support HardSwish
by Diqing Zhong
· 3 years, 5 months ago
2c2522d
MLBEDSW-3772 Fix FC with changed inp shape
by Patrik Gustavsson
· 3 years, 5 months ago
7bada40
MLBEDSW-3772 Fix unfusing ConcatTFlite
by Patrik Gustavsson
· 3 years, 5 months ago
3a26920
MLBEDSW-3772 Reshape removal
by Patrik Gustavsson
· 3 years, 5 months ago
e22ba8c
[MLBEDSW-3891] Fix reading back in an ethos-u custom op
by Fredrik Svedberg
· 3 years, 5 months ago
6023214
MLBEDSW-3832: mlw_codec: improve C API
by Louis Verhaard
· 3 years, 5 months ago
b218376
MLBEDSW-3847: MLCE: Vela not handling multiple custom operators correctly
by Tim Hall
· 3 years, 5 months ago
8af061a
MLBEDSW-3832: Search allocator: improve C API
by Louis Verhaard
· 3 years, 5 months ago
ece4e65
MLBEDSW-3418: Bug fixes 16-bit leaky relu
by Louis Verhaard
· 3 years, 6 months ago
d4738e5
MLBEDSW-3843: Segmentation fault search allocator
by Louis Verhaard
· 3 years, 5 months ago
606063f
MLBEDSW-3736: Replaced placeholder type annotations
by erik.andersson@arm.com
· 3 years, 5 months ago
7b67649
MLBEDSW-3858: Incorrect PAD usage bug
by erik.andersson@arm.com
· 3 years, 5 months ago
e82be7c
[MLBEDSW-2787] Remove op.attrs["rescale"] in softmax.py
by Fredrik Svedberg
· 3 years, 5 months ago
db5124c
MLBEDSW-3144: Add weights compression ratio
by Diqing Zhong
· 3 years, 6 months ago
9a0cff1
MLBEDSW-3418: More operator checks for infinity
by Louis Verhaard
· 3 years, 6 months ago
224e99b
MLBEDSW-3654 Fix for split/concat ops
by Patrik Gustavsson
· 3 years, 6 months ago
49b4f1c
MLBEDSW-3769: Fix print error
by Diqing Zhong
· 3 years, 6 months ago
0a261cd
MLBEDSW-3804 Add missing check for npu_op
by Patrik Gustavsson
· 3 years, 6 months ago
70b71a5
MLBEDSW-3763: Vela memory setting
by Tim Hall
· 3 years, 6 months ago
c509d33
MLBEDSW-3654 Fix setting op ifm ofm for LeakyRelu
by Patrik Gustavsson
· 3 years, 6 months ago
69b8480
MLBEDSW-3495: Tensor resampling mode for transpose
by Louis Verhaard
· 3 years, 7 months ago
f4e12be
MLBEDSW-3561: Support const STRING input tensors
by Louis Verhaard
· 3 years, 7 months ago
f27a8b6
MLBEDSW-3711: Added operator checks for PAD.
by Erik Andersson
· 3 years, 7 months ago
ae2d553
MLBEDSW-3499: Support for PAD operator
by Louis Verhaard
· 3 years, 7 months ago
016b827
MLBEDSW-1493: Optimise strided conv
by Diqing Zhong
· 3 years, 7 months ago
3d73717
MLBEDSW-3791 Fix converting axis to 4D axis
by Patrik Gustavsson
· 3 years, 6 months ago
cc6915c
MLBEDSW-3790 Fix for cpu ops has no op.ifm_shapes
by Patrik Gustavsson
· 3 years, 6 months ago
6bb8f67
MLBEDSW-3786 Fix index out of range on ofm_shapes
by Patrik Gustavsson
· 3 years, 6 months ago
eeb8515
Revert "Revert "MLBEDSW-3645 4D class for op ifm/ofm shapes""
by patrik.gustavsson
· 3 years, 6 months ago
df0a590
Revert "MLBEDSW-3645 4D class for op ifm/ofm shapes"
by patrik.gustavsson
· 3 years, 6 months ago
bf31d64
MLBEDSW-3645 4D class for op ifm/ofm shapes
by Patrik Gustavsson
· 3 years, 7 months ago
2349d42
MLBEDSW-3654 Add/use op ifm/ofm shapes
by Patrik Gustavsson
· 3 years, 7 months ago
528a56d
vela: Move special error cases
by Michael McGeagh
· 3 years, 7 months ago
1a184e4
[MLBEDSW-3687] Update setup.py with new OS support
by Fredrik Svedberg
· 3 years, 7 months ago
5b51388
[MLBEDSW-297] Setup and run on Microsoft Windows
by Fredrik Svedberg
· 3 years, 7 months ago
6c74c3b
MLBEDSW-3487: Support '<' for tensors
by Louis Verhaard
· 3 years, 7 months ago
1689548
MLBEDSW-3694 Replace padding with enum
by Michael McGeagh
· 3 years, 7 months ago
f842b69
MLBEDSW-3465: Add memory settings into sys config
by Diqing Zhong
· 3 years, 7 months ago
7a6f843
MLBEDSW-2066 Improve Exception messages
by Michael McGeagh
· 3 years, 7 months ago
9b43f84
MLBEDSW-3653: Fix type errors in annotated files
by Dwight Lidman
· 3 years, 7 months ago
94457b1
Revert "Revert "MLMBED-3450: Do not convert batched fully connected to conv""
by Diqing Zhong
· 3 years, 7 months ago
9bfe0f8
MLBEDSW-1373: Added search based allocator
by Louis Verhaard
· 3 years, 7 months ago
93719a9
MLBEDSW-3653: Added type hints to tensor.py
by Louis Verhaard
· 3 years, 7 months ago
5401823
vela: Update pre-commit
by Michael McGeagh
· 3 years, 7 months ago
69aadd0
Vela: bandwidth calculation improvements
by Diqing Zhong
· 3 years, 7 months ago
2fa40ae
MLBEDSW-3333 New CLI: --verbose-all
by Michael McGeagh
· 3 years, 7 months ago
f3e3ad7
MLBEDSW-2836 Change sets to tuples
by Michael McGeagh
· 3 years, 7 months ago
d9c2c42
[MLBEDSW-3690] Refactor Softmax
by Fredrik Svedberg
· 3 years, 7 months ago
d5cf765
vela: Modify CFLAGS for mlw_codec makefile
by Michael McGeagh
· 3 years, 7 months ago
6f72526
MLBEDSW-3685 Fix dangerous default value usage
by Michael McGeagh
· 3 years, 7 months ago
1e05afa
vela: Further improve readme regex in setup.py
by Michael McGeagh
· 3 years, 7 months ago
1e17018
MLBEDSW-3643: Refactor blockdep calculation
by Louis Verhaard
· 3 years, 7 months ago
32c7f5b
Softmax use f-strings
by Fredrik Svedberg
· 3 years, 7 months ago
44c6fe9
vela: Improve regex for readme link replacement
by Michael McGeagh
· 3 years, 7 months ago
2.0.1
b27d895
Regenerated supported operators file
by Jacob Bohlin
· 3 years, 7 months ago
2.0.0
2.0.0.rc3
e3de4e5
MLBEDSW-3633: SplitV incorrectly placed on CPU
by Jacob Bohlin
· 3 years, 7 months ago
333770a
MLBEDSW-3606: Update release notes
by Tim Hall
· 3 years, 7 months ago
14e8a20
vela: Rename --keep-scale-placement CLI
by Tim Hall
· 3 years, 7 months ago
061eeb4
MLBEDSW-3424 Arch cache
by Louis Verhaard
· 3 years, 7 months ago
d266580
MLBEDSW-3562: Improve blockdep calculation
by Louis Verhaard
· 3 years, 7 months ago
603016c
MLBEDSW-3024 Updated OPTIONS.md
by Michael McGeagh
· 3 years, 7 months ago
a578e2f
MLBEDSW-3024 Added and updated EthosU weblinks
by Michael McGeagh
· 3 years, 7 months ago
c21d1c7
MLBEDSW-3583: Prevent DMA for converted FullyConnected
by Louis Verhaard
· 3 years, 7 months ago
0dd21c7
MLBEDSW-3558: Put FC on CPU when OFM != 2D
by Dwight Lidman
· 3 years, 7 months ago
Next »