[PR #809] [MERGED] fix: regression unsupported metal types #88322

Closed
opened 2026-05-10 07:05:07 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/809
Author: @mxyng
Created: 10/16/2023
Status: Merged
Merged: 10/17/2023
Merged by: @mxyng

Base: mainHead: mxyng/fix-gpu


📝 Commits (1)

  • cb4a80b fix: regression unsupported metal types

📊 Changes

1 file changed (+1 additions, -4 deletions)

View changed files

📝 llm/llama.go (+1 -4)

📄 Description

omitting --n-gpu-layers means use metal on macos which isn't correct since ollama uses num_gpu=0 to explicitly disable gpu for file types that are not implemented in metal


🔄 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/809 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 10/16/2023 **Status:** ✅ Merged **Merged:** 10/17/2023 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `mxyng/fix-gpu` --- ### 📝 Commits (1) - [`cb4a80b`](https://github.com/ollama/ollama/commit/cb4a80b6934c1b62c98a01aab4ae156ba340acc5) fix: regression unsupported metal types ### 📊 Changes **1 file changed** (+1 additions, -4 deletions) <details> <summary>View changed files</summary> 📝 `llm/llama.go` (+1 -4) </details> ### 📄 Description omitting `--n-gpu-layers` means use metal on macos which isn't correct since ollama uses `num_gpu=0` to explicitly disable gpu for file types that are not implemented in metal --- <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 2026-05-10 07:05:07 -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#88322