ONNX GenAI
Collection
A collection of models that are able to be run using onnxruntime-genai and can be served through embeddedllm library.
•
13 items
•
Updated
•
2
Gemma-2B-Instruct-ONNX
Model Summary
This repository contains optimized versions of the gemma-2b-it model, designed to accelerate inference using ONNX Runtime. These optimizations are specifically tailored for CPU and DirectML. DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning, offering GPU acceleration across a wide range of supported hardware and drivers, including those from AMD, Intel, NVIDIA, and Qualcomm.
ONNX Models
Here are some of the optimized configurations we have added:
- ONNX model for int4 DirectML: ONNX model for AMD, Intel, and NVIDIA GPUs on Windows, quantized to int4 using AWQ.
- ONNX model for int4 CPU and Mobile: ONNX model for CPU and mobile using int4 quantization via RTN. There are two versions uploaded to balance latency vs. accuracy. Acc=1 is targeted at improved accuracy, while Acc=4 is for improved performance. For mobile devices, we recommend using the model with acc-level-4.
Usage
Installation and Setup
To use the Gemma-2B-Instruct-ONNX model on Windows with DirectML, follow these steps:
- Create and activate a Conda environment:
conda create -n onnx python=3.10
conda activate onnx
- Install Git LFS:
winget install -e --id GitHub.GitLFS
- Install Hugging Face CLI:
pip install huggingface-hub[cli]
- Download the model:
huggingface-cli download EmbeddedLLM/gemma-2b-it-onnx --include="onnx/directml/*" --local-dir .\gemma-2b-it-onnx
- Install necessary Python packages:
pip install numpy==1.26.4
pip install onnxruntime-directml
pip install --pre onnxruntime-genai-directml
- Install Visual Studio 2015 runtime:
conda install conda-forge::vs2015_runtime
- Download the example script:
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/phi3-qa.py" -OutFile "phi3-qa.py"
- Run the example script:
python phi3-qa.py -m .\gemma-2b-it-onnx
Hardware Requirements
Minimum Configuration:
- Windows: DirectX 12-capable GPU (AMD/Nvidia)
- CPU: x86_64 / ARM64
Tested Configurations:
- GPU: AMD Ryzen 8000 Series iGPU (DirectML)
- CPU: AMD Ryzen CPU