ONE

ONE copied to clipboard

[doc] Update how-to-build-runtime.md

2

This commit updates how-to-build-runtime.md. - Add installing libglib2.0-dev for x64 build ONE-DCO-1.0-Signed-off-by: ragmani

ragmani

[infra] Add cortex-m7 platform

2

This commit addds cortex-m7 to supported platforms. ONE-DCO-1.0-Signed-off-by: Vyacheslav Bazhenov [email protected]

SlavikMIPT

[onert] Version up Ruy library

2

### What? Let's upgrade Ruy library version (ruy for TFLite 2.3 -> 2.8) ### Why? - Resolve issue #9265 - Prepare TFLite test tool version up

hseok-oh

[onert] Run Batch request in parallel manner via direct call to trix-engine

22

This is for tracking "Milestone1 : Run Batch request in parallel manner via direct call to trix-engine(~Tizen M2, Aug 30th)" from https://github.com/Samsung/ONE/projects/8 ## User scenario - User will use nnfw...

chunseoklee

This commit adds an option `--parallel_inputs`. ONE-DCO-1.0-Signed-off-by: ragmani Related issue: #9207

ragmani

[tflchef-reverse] Support Densify

1

Let's support Densify in tflchef-reverse. This task is not urgent and added not to forget after supporting Densify operator in compiler.

seanshpark

[onert] Support TFlite 2.8 for gpu_cl

18

1. Update the tensorflow version used in gpu_cl to 2.8. 2. I added config file to download source code to build tensorflow lite 2.8. 3. Applied changed api with update...

YiHyunJin

## What Let's support quantization of hybrid FullyConnected Op (int8 weights/float32 input -> uint8 weights/uint8 input or int16 weights/int16 input). Parent issue: https://github.com/Samsung/ONE/issues/9535

jinevening

## What Let's support quantization of (TF-style) hybrid Ops whose input feature map is float32 and weights(filters) are quantized. List of hybrid Ops - FullyConnected - Conv2D - DepthwiseConv2D -...

jinevening

[onert] User Scenario of On-Device Compiler on ONERT

7

Let's consider user scenario with on-device compiler on onert.

chunseoklee