EdgeML
uTensor
| EdgeML | uTensor | |
|---|---|---|
| 1 | 1 | |
| 1,541 | 1,651 | |
| 0.8% | 1.0% | |
| 0.0 | 1.9 | |
| about 1 month ago | 18 days ago | |
| C++ | C++ | |
| GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
EdgeML
-
Great Quantization Libraries? [D]
There is compiler from microsoft called SEEDOT https://github.com/microsoft/EdgeML/tree/master/tools/SeeDot , very good for 8bit , not sure for 4bit , what is usecase you compile it down to 4 bit systems
uTensor
-
[D] why isn't converting ML Models to plain code trivial?
Random example, more stuff. My comments are more of baking models into c(pp) code which is not what cppflow does but probably what you are actually looking for.
What are some alternatives?
tinyengine - [NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
ESP32-S2-S3-Projects - Using the native USB interface of ESP32 S2/S3
MetisFL - The first open Federated Learning framework implemented in C++ and Python.
EmbeddedProto - Embedded Proto is a C++ Protocol Buffers implementation specifically suitable for microcontrollers. It is small, reliable and easy to use.
nebuly - The user analytics platform for LLMs
areg-sdk - AREG is an asynchronous Object RPC framework to simplify multitasking programming by blurring borders between processes and treating remote objects as if they coexist in the same thread.
vit.cpp - Inference Vision Transformer (ViT) in plain C/C++ with ggml
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
frugally-deep - Header-only library for using Keras (TensorFlow) models in C++.
DeepSpeech - DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
blynk-library - Blynk library for IoT boards. Works with Arduino, ESP32, ESP8266, Raspberry Pi, Particle, ARM Mbed, etc.
Postform - Postponed formatting experiments with string interning in C++. Inspired by the defmt Rust crate