Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
This innovative tool is designed for quantizing convolutional neural networks (CNNs). It allows for the transformation of both weights/biases and activations from 32-bit floating-point (FP32) to 8-bit integer (INT8) format, or even other bit depths. Utilizing this tool can greatly enhance inference performance and efficiency, all while preserving accuracy levels. It is compatible with various common layer types found in neural networks, such as convolution, pooling, fully-connected layers, and batch normalization, among others. Remarkably, the quantization process does not require the network to be retrained or the use of labeled datasets; only a single batch of images is sufficient. Depending on the neural network's size, the quantization can be completed in a matter of seconds to several minutes, facilitating quick updates to the model. Furthermore, this tool is specifically optimized for collaboration with DeePhi DPU and can generate the INT8 format model files necessary for DNNC integration. By streamlining the quantization process, developers can ensure their models remain efficient and robust in various applications.
Description
ExecuTorch is an open-source framework developed for PyTorch, specifically designed to deploy AI and machine learning models directly onto edge devices, facilitating tasks such as text, vision, speech, recommendation, and multimodal inference without the need for cloud connectivity. This framework allows for the exportation of models from PyTorch without any need for intermediate conversion formats, effectively maintaining ATen operators and employing ahead-of-time compilation to enhance performance tailored to specific hardware prior to deployment. Developers benefit from a modular architecture that offers flexibility in selecting both compile-time and runtime optimizations, all within the well-known PyTorch environment, which includes torchao specifically for quantization. With a lightweight C++ runtime that occupies roughly 50 KB, ExecuTorch is versatile enough to operate on a variety of platforms, including smartphones, desktops, embedded systems, microcontrollers, DSPs, and Cortex-M processors. It is compatible with multiple operating systems such as Android, iOS, Linux, Windows, macOS, and WebAssembly, and offers native APIs in C++, Swift, Kotlin, and Objective-C. As a result, ExecuTorch provides developers with a powerful tool to streamline the deployment of AI models across diverse devices and applications.
API Access
Has API
No
API Access
Has API
Yes
Integrations
C++
No
Facebook
No
Instagram
No
Kotlin
No
LLaVA
No
Llama 3.2
No
Muse Glimmer
No
Objective-C
No
OpenAI Whisper
No
Phi-4-mini-reasoning
No
Integrations
C++
Yes
Facebook
Yes
Instagram
Yes
Kotlin
Yes
LLaVA
Yes
Llama 3.2
Yes
Muse Glimmer
Yes
Objective-C
Yes
OpenAI Whisper
Yes
Phi-4-mini-reasoning
Yes
Pricing Details
$0.90 per hour
Free Trial
No
Free Version
No
Pricing Details
Free
Free Trial
No
Free Version
Yes
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
No
On-Premises
Yes
iPhone App
Yes
iPad App
Yes
Android App
Yes
Windows
Yes
Mac
Yes
Linux
Yes
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
DeePhi Quantization Tool
Website
aws.amazon.com/marketplace/pp/prodview-bwtx6kzwg3gva
Vendor Details
Company Name
ExecuTorch
Country
United States
Website
executorch.ai/