Skip to content

Instantly share code, notes, and snippets.

@jammm

jammm/collect.md

Last active December 16, 2025 22:50
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save jammm/3954a7ed521181b36e449c9a1a797af4 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save jammm/3954a7ed521181b36e449c9a1a797af4 to your computer and use it in GitHub Desktop.
Download ZIP
Collecting data on MIOpen and hipBLASLt shapes
Raw
collect.md

Are you facing slow performance when running your models using ComfyUI/SD WebUI or any pytorch program using your Radeon 9070XT, AI Pro R9700, or Strix Halo (Radeon 8060S) ? Then we need your help! Please provide us performance logs when running your models. It will help us tune our libraries for better performance on your models.

Please set the following environment variables depending on your OS:

Windows (powershell)

$env:MIOPEN_ENABLE_LOGGING=1
$env:MIOPEN_ENABLE_LOGGING_CMD=1
$env:HIPBLASLT_LOG_MASK=32
$env:TORCH_BLAS_PREFER_HIPBLASLT=1
$env:HIPBLASLT_LOG_FILE="your_model_hipblaslt_log.txt"

Linux:

export MIOPEN_ENABLE_LOGGING=1
export MIOPEN_ENABLE_LOGGING_CMD=1
export HIPBLASLT_LOG_MASK=32
export TORCH_BLAS_PREFER_HIPBLASLT=1
export HIPBLASLT_LOG_FILE="your_model_hipblaslt_log.txt"

Then run your workload as usual, for example, SD WebUI, your pytorch scripts, or ComfyUI, using <command> > miopen_output_logs.txt on the same terminal as you used to run the above commands.

Then share with us the output logs from hipBLASLt (your_model_hipblaslt_log.txt) and output+MIOpen logs miopen_output_logs.txt from the terminal output in the comments below.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment