Skip to content

Instantly share code, notes, and snippets.

@Basten7
Last active September 10, 2025 14:59
Show Gist options
  • Select an option

  • Save Basten7/091df055c04edaa9c88eb0cdc7fc429d to your computer and use it in GitHub Desktop.

Select an option

Save Basten7/091df055c04edaa9c88eb0cdc7fc429d to your computer and use it in GitHub Desktop.
Prompt Processing vs Token Generation
Classic LLM-inference trace on the GPU
@Basten7
Copy link
Author

Basten7 commented Aug 11, 2025

LLM-inference trace on Metal3 Build at 0.1 ms
Capture d’écran 2025-08-11 à 11 00 29

LLM-inference trace on Vulkan Build at 0.1 ms
Capture d’écran 2025-08-11 à 10 59 46

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