larq/compute-engine

View on GitHub

Highly optimized inference engine for Binarized Neural Networks

Stars: 258
Forks: 35
Open beginner issues: 0
Indexed issues: 17

Dominant language: C++
License: Apache-2.0
Last GitHub push: Jul 30, 2026
Latest indexed: Sep 18, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: good first issue
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

17 open issues indexed

Does LCE support deployment on ARM32 Cortex-M7? Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

larq/compute-engine#814 · 3 comments · Opened Nov 7, 2024
Cannot save compressed binary or ternary weights, saved as float32 parameters Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

larq/compute-engine#806 · 12 comments · Opened Jun 11, 2024
Larq Compute Engine seems incompatible with tensorflow-lite-task-vision on Android (using the latest tensorflow lite demo code) Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

larq/compute-engine#800 · 2 comments · Opened Jan 26, 2024
extra model size induced by non-parameter layer Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

larq/compute-engine#773 · 1 comment · Opened May 6, 2023
Bool input tensor Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

larq/compute-engine#771 · 7 comments · Opened Apr 19, 2023
DoReFa quantizer with higher number of MACs/Ops, Grouped convs as custom ops on LCE 0.7.0 Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

larq/compute-engine#745 · 3 comments · Opened Jul 20, 2022
`convert_keras_model()` does not work as expected for BinaryDenseNet37 Dilated and XNORNet Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 25/100

larq/compute-engine#744 · 1 comment · Opened Jul 14, 2022
LCEInterpreter and converter design Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

larq/compute-engine#713 · 1 comment · Opened Feb 17, 2022
Add support for bitpacked activations in optimized ARM32 kernels Open

feature good first issue

Difficulty 4/5 3-5 days Newbie friendliness 30/100

larq/compute-engine#647 · 2 reactions · Opened May 20, 2021
Warn users when converting models which can't be optimally accelerated Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

larq/compute-engine#542 · 1 comment · Opened Oct 21, 2020
Int8 default ranges break when a bconv is followed by a normal conv. Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 45/100

larq/compute-engine#421 · 5 comments · Opened Jul 2, 2020
Add MLIR verifier to BConv op Open

good first issue internal-improvement

Difficulty 3/5 1-2 days Newbie friendliness 42/100

larq/compute-engine#406 · Opened Jun 15, 2020
RFC: Create a Packed datatype Open

internal-improvement

Difficulty 5/5 Over a week Newbie friendliness 35/100

larq/compute-engine#325 · 1 comment · Opened Apr 3, 2020
Creating LCE compatible TFLite iOS apps Open

good first issue

larq/compute-engine#285 · 2 comments · 1 assignee · Opened Mar 15, 2020
add clang-tidy to CI Open

good first issue

Difficulty 4/5 3-5 days Newbie friendliness 25/100

larq/compute-engine#284 · 1 comment · Opened Mar 15, 2020
investigating TF lite SELECTIVE_REGISTRATION feature Open

wont fix soon

Difficulty 5/5 Over a week Newbie friendliness 25/100

larq/compute-engine#76 · 1 comment · Opened Oct 23, 2019
add binary fully connected operator Open

feature

Difficulty 5/5 Over a week Newbie friendliness 20/100

larq/compute-engine#53 · 4 comments · Opened Oct 7, 2019

larq/compute-engine

Get new issues in your inbox