FakeAudio ONNX used for the VAIML reproduction

This repository contains the exact FakeAudio ONNX artifact tested in odobias/amd-vaiml-window-partition-repro. It is published separately so AMD and other investigators can reproduce the VAIML compilation result without access to the private benchmark asset store.

Artifact

  • File: model.onnx
  • Size: 127,844,774 bytes
  • SHA-256: d4b2dde8f4f95862ecb9f5e90821d853adea3774e7c48857f60ee6084d5e85c6
  • ONNX opset: 17
  • Producer recorded in ONNX: PyTorch 2.1.2

The ONNX file contains no additional provenance metadata.

Download

hf download odobias/fakeaudio-onnx-vaiml-repro model.onnx --local-dir .

Verify the downloaded artifact before reproducing the result:

(Get-FileHash .\model.onnx -Algorithm SHA256).Hash.ToLowerInvariant()

Observed VAIML result

With Ryzen AI SDK 1.8.0-beta on an AMD Ryzen AI 9 HX 370, AMD's BF16 VAIML configuration fails flexible L1 buffer placement at layer 224. ONNX Runtime then executes the entire optimized graph on CPU: 0 NPU nodes, 512 CPU nodes, and 100% CPU offload.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support