metadata

license: mit
pipeline_tag: text-generation
tags:
  - ONNX
  - DML
  - ONNXRuntime
  - phi3
  - nlp
  - conversational
  - custom_code
inference: false
language:
  - en

EmbeddedLLM/Phi-3-mini-4k-instruct-062024-int4-onnx-directml

Model Summary

This model is an ONNX-optimized version of microsoft/Phi-3-mini-4k-instruct (June 2024), designed to provide accelerated inference on a variety of hardware using ONNX Runtime(CPU and DirectML). DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning, providing GPU acceleration for a wide range of supported hardware and drivers, including AMD, Intel, NVIDIA, and Qualcomm GPUs.

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.

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

Model Description

Developed by: Microsoft
Model type: ONNX
Language(s) (NLP): Python, C, C++
License: Apache License Version 2.0
Model Description: This model is a conversion of the Phi-3-mini-4k-instruct-062024 for ONNX Runtime inference, optimized for DirectML.

Performance Metrics

DirectML

We measured the performance of DirectML on AMD Ryzen 9 7940HS /w Radeon 78

Prompt Length	Generation Length	Average Throughput (tps)
128	128	-
128	256	-
128	512	-
128	1024	-
256	128	-
256	256	-
256	512	-
256	1024	-
512	128	-
512	256	-
512	512	-
512	1024	-
1024	128	-
1024	256	-
1024	512	-
1024	1024	-