Skip to content
ModelListedExternal
Browse files

Fakeaudio Onnx Vaiml Repro

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...

Sourcehuggingface.co/odobias/fakeaudio-onnx-vaiml-repro/tree/da5acae80b8a2db207f20e88aa4b64d09a5cb57c
KindOtherVersionRevision da5acaeCgrade

Model source

Kind
Other
File size
4.14–122 MB
Version
vRevision da5acae
Updated
Oct 19, 2026
Downloads
0
Source
Hugging Face

Source description

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.

Sources

1 source
Hugging FacePrimaryVersion da5acae80b8a2db207f20e88aa4b64d09a5cb57c
huggingface.co/odobias/fakeaudio-onnx-vaiml-repro/tree/da5acae80b8a2db207f20e88aa4b64d09a5cb57c

Verified Oct 19

Download files

Model artifacts

4 artifacts

model.backbone-fp32.onnx

onnx · 118 MB · SHA-256 c0fcc366e5ea…f205 · Hugging Face

Download file

model.backbone.expanded-attention-bias.onnx

onnx · 118 MB · SHA-256 5cf550bcd87f…632e · Hugging Face

Download file

model.frontend-fp32.onnx

onnx · 4.14 MB · SHA-256 37fe1acb80db…d179 · Hugging Face

Download file

model.onnx

onnx · 122 MB · SHA-256 d4b2dde8f4f9…85c6 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 2huggingface.co/odobias/fakeaudio-onnx-vaiml-repro

--- tags: - onnx - audio-classification - ryzen-ai - vitis-ai library_name: onnxruntime --- # FakeAudio ONNX used for the VAIML reproduction This repository contains the exact FakeAudio ONNX artifact tested in [`odobias/amd-vaiml-window-partition-repro`](https://github.com/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 ```powershell hf download odobias/fakeaudio-onnx-vaiml-repro model.onnx --local-dir . ``` Verify the downloaded artifact before reproducing the result: ```powershell (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.

NoteAug 2huggingface.co/odobias/fakeaudio-onnx-vaiml-repro

Source context: 0 downloads · 0 likes · Pipeline audio-classification · Library onnxruntime · Repo odobias/fakeaudio-onnx-vaiml-repro