[PR #4068] [MERGED] metal: add 512MiB to minimum memory, no partial offloading overhead #73665

Closed
opened 2026-05-05 05:35:54 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/4068
Author: @jmorganca
Created: 5/1/2024
Status: Merged
Merged: 5/1/2024
Merged by: @jmorganca

Base: mainHead: jmorgan/macos-estimates


📝 Commits (1)

  • 1c63ed8 gpu: add 512MiB to darwin minimum, metal doesn't have partial offloading overhead

📊 Changes

2 files changed (+12 additions, -1 deletions)

View changed files

📝 gpu/gpu_darwin.go (+7 -1)
📝 llm/memory.go (+5 -0)

📄 Description

No description provided


🔄 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/4068 **Author:** [@jmorganca](https://github.com/jmorganca) **Created:** 5/1/2024 **Status:** ✅ Merged **Merged:** 5/1/2024 **Merged by:** [@jmorganca](https://github.com/jmorganca) **Base:** `main` ← **Head:** `jmorgan/macos-estimates` --- ### 📝 Commits (1) - [`1c63ed8`](https://github.com/ollama/ollama/commit/1c63ed8ef6a1b2405590a5dbc8f28d4edd46cee7) gpu: add 512MiB to darwin minimum, metal doesn't have partial offloading overhead ### 📊 Changes **2 files changed** (+12 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `gpu/gpu_darwin.go` (+7 -1) 📝 `llm/memory.go` (+5 -0) </details> ### 📄 Description _No description provided_ --- <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 2026-05-05 05:35:54 -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#73665