Release v1.6.0

Release Note: Version 1.6.0

• BF16 Compiler (CNN, Transformer, ASR)

  • BF16 CNN perf improvements average 80% across release

  • BF16 perf improvements - 1.3X faster on CNN than iGPU and 2.6X faster for transformers than iGPU

  • Improved coverage and improved performance for ASR models

  • Average 3x compile time improvement

  • Smaller installation size

  • Reduction in CPU overhead by pushing data layout transformation to NPU

  • Dynamic batch size support for compilation

• New Integer Compiler (CNN)

  • Support for General Asymmetric Quantization enabling third party quantized models to run on NPU
  • Support for XINT8, A8W8, A16W8

• LLM

  • Broad Set of NPU only models optimized performance
  • New set of hybrid models with bfp16 activation
  • New architecture support in hybrid flow (Phi-4, Qwen-3)
  • Context length improvement from 2K to 4K for all models.

• Stable Diffusion Demo

  • 8x Dynamic Resolution for SD3.0/3.5 (text2image and image2imageControlNet)
  • Performance boost for SD 1.5/2.1-base/turbo/XL-turbo
    Support Batch Size 1 for SD-turbo/SDXL-turbo
    New model support (SD2.1-v 768x768 text2image, SDXL-base 1024x1024 text2image)

• Breaking Changes

  • For running INT8 models on STX/KRK or newer devices, the xclbin provider option is no longer supported and should no longer be used. See Using INT8 Models for full details.

  • For running INT8 models on PHX/HPT devices, the target option should be set to X1. The NPU binary should still be specified using the xclbin provider option. See Using INT8 Models for full details.

  • For BF16 models, the default configurations file requires a new target section. See Config File Options for full details.

  • LLM:

    • OGA version has been updated to v0.9.2 (Ryzen AI 1.6) from v0.7.0 (Ryzen AI 1.5). Any APIs that are obsolete must be updated to the supported equivalents as described in the Microsoft ONNX Runtime GenAI v0.9.2 documentation
    • Hybrid models published with earlier releases are not compatible with Ryzen AI 1.6. Please use the hybrid models published with the 1.6 release.

Release v1.5.0

Release Note: Version 1.5.0

• EoU Improvement

  • Application concurrency: improves the resource distribution across applications
  • Model Compilation time: 2x – 8x faster
  • Installation Size: 80% smaller

• New getting started tutorial with fine-tuned ResNet BF16 model using Python / C++ for deployment on NPU

• New object detection tutorial with Yolov8m model with BF16 / XINT8 quantization using AMD-Quark

• Multi-model demo has been removed

• Support for New LLMs released

  • Qwen/Qwen2.5-1.5B-Instruct
  • Qwen/Qwen2.5-3B-Instruct
  • Qwen/Qwen2.5-7B-Instruct

• Bug fixes

• Breaking Changes

  • The %RYZEN_AI_INSTALLATION_PATH%\deployment folder has been reorganized and flattened. Deployment DLLs are no longer organized in subfolders. If you use application build scripts that pull DLLs from the deployment folder, you need to update them based on the new paths. Refer to the :ref:Application Packaging Requirements <app-packaging> section for further details.

  • The 1x4.xclbin (PHX/HPT) and AMD_AIE2P_Nx4_Overlay.xclbin (STX/KRK) NPU binaries are no longer supported and should not be used. You should use the 4x4.xclbin (PHX/HPT) and AMD_AIE2P_4x4_Overlay.xclbin (STX/KRK) NPU binaries instead.

  • The XLNX_ENABLE_CACHE, XLNX_VART_FIRMWARE, and XLNX_TARGET_NAME environment variables are no longer supported and should not be relied upon.

  • Support for VitisAI EP cache encryption is no longer available. To encrypt the compiled models, use the ONNX Runtime :ref:EP Context Cache <ort-ep-context-cache> feature instead.

  • For INT8 models, the VitisAI EP does not save the compiled model to disk by default. To save the compiled model, use the ONNX Runtime :ref:EP Context Cache <ort-ep-context-cache> feature or set the :option:enable_cache_file_io_in_mem provider option to 0.

  • Generation of the vitisai_ep_report.json file is no longer automatic and should be manually enabled. See the :ref:Operator Assignment Report <op-assignment-report> section for details.

  • Changes to the OGA flow for LLMs:

    • OGA Version is updated to v0.7.0 (Ryzen AI 1.5) from v0.6.0 (Ryzen AI 1.4).
    • The hybrid_llm and npu_llm folders are consolidated into a new folder named LLM, which contains the model_benchmark.exe and run_model.py scripts, along with the necessary C++ headers and .lib files to support both the Hybrid LLM and NPU LLM workflows in C++ and Python.
    • For NPU LLM models, the vaip_llm.json file is no longer required. As a result, the vaip_llm.json path is removed from the genai_config.json for all NPU models. Ensure that you re-download the NPU models from Hugging Face <https://huggingface.co/collections/amd/ryzenai-15-llm-npu-models-6859846d7c13f81298990db0>_ when using the Ryzen AI 1.5 installer.

Release v1.4.0

Merge pull request #173 from cyndwith/resnet_config

removing the optional configuration option

Release v1.3.1

Merge pull request #161 from jeremyfowers/main

Add DeepSeek-R1-Distill CPU examples

Release v1.2.0

Merge pull request #119 from cyndwith/main

Updates to the RyzenAI-SW demos, examples and tutorials