[PR #824] [MERGED] fix MB VRAM log output #10345

Closed
opened 2026-04-12 22:58:38 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/824
Author: @BruceMacD
Created: 10/17/2023
Status: Merged
Merged: 10/17/2023
Merged by: @BruceMacD

Base: mainHead: brucemacd/vram-log


📝 Commits (1)

📊 Changes

1 file changed (+1 additions, -1 deletions)

View changed files

📝 llm/llama.go (+1 -1)

📄 Description

This was logging the bytes:

15651045376 MiB VRAM available, loading up to 29 GPU layers

Fix:

14926 MB VRAM available, loading up to 29 GPU layers

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/824 **Author:** [@BruceMacD](https://github.com/BruceMacD) **Created:** 10/17/2023 **Status:** ✅ Merged **Merged:** 10/17/2023 **Merged by:** [@BruceMacD](https://github.com/BruceMacD) **Base:** `main` ← **Head:** `brucemacd/vram-log` --- ### 📝 Commits (1) - [`b925c2f`](https://github.com/ollama/ollama/commit/b925c2f17201464cbb8d7868c01f867c80c34839) fix MB VRAM log output ### 📊 Changes **1 file changed** (+1 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `llm/llama.go` (+1 -1) </details> ### 📄 Description This was logging the bytes: ``` 15651045376 MiB VRAM available, loading up to 29 GPU layers ``` Fix: ``` 14926 MB VRAM available, loading up to 29 GPU layers ``` --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-12 22:58:38 -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#10345