vit.cpp
EdgeML
vit.cpp | EdgeML | |
---|---|---|
2 | 1 | |
177 | 1,541 | |
- | 0.8% | |
8.8 | 0.0 | |
29 days ago | about 1 month ago | |
C++ | C++ | |
MIT License | GNU General Public License v3.0 or later |
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.
vit.cpp
-
I've open sourced my Flutter plugin to run on-device LLMs on any platform. TestFlight builds available now.
And more stuff I’m often checking back on: - https://github.com/staghado/vit.cpp - https://github.com/serp-ai/bark-with-voice-clone - https://github.com/leejet/stable-diffusion.cpp (generate images) - etc … there’s too much fun stuff out there. Wish I had more free time haha.
-
[P] Inference Vision Transformer (ViT) in plain C/C++ with ggml
You can access it here: https://github.com/staghado/vit.cpp It has been added to the ggml library on GitHub: https://github.com/ggerganov/ggml
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
What are some alternatives?
stable-diffusion.cpp - Stable Diffusion in pure C/C++
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
minigpt4.cpp - Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)
MetisFL - The first open Federated Learning framework implemented in C++ and Python.
Daisykit - Daisykit is an easy AI toolkit with face mask detection, pose detection, background matting, barcode detection, and more. With Daisykit, you don't need AI knowledge to build AI software.
nebuly - The user analytics platform for LLMs
tokay-lite-sdk - Tokay Lite: Low Power Edge AI Camera SDK
bark.cpp - Port of Suno AI's Bark in C/C++ for fast inference
frugally-deep - A lightweight header-only library for using Keras (TensorFlow) models in C++.
ggml - Tensor library for machine learning
web_ffi - Translates dart:ffi calls on the web to WebAssembly using dart:js