[PR #11332] ggml: Use assigned layers when reporting loading stats #13512

Closed
opened 2026-04-13 00:29:13 -05:00 by GiteaMirror · 0 comments
Owner

Original Pull Request: https://github.com/ollama/ollama/pull/11332

State: closed
Merged: Yes


Reporting params.NumGPULayers can be misleading because it is the requested number of layers, not the actual number that is loaded. While they are often the same, there are cases where they might mismatch, such as if the GPU backend is missing.

**Original Pull Request:** https://github.com/ollama/ollama/pull/11332 **State:** closed **Merged:** Yes --- Reporting params.NumGPULayers can be misleading because it is the requested number of layers, not the actual number that is loaded. While they are often the same, there are cases where they might mismatch, such as if the GPU backend is missing.
GiteaMirror added the pull-request label 2026-04-13 00:29:13 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#13512