[PR #520] [MERGED] Fix ggml arm64 linux cuda build #20735

Closed
opened 2026-04-19 15:13:34 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/520
Author: @BruceMacD
Created: 9/12/2023
Status: Merged
Merged: 9/12/2023
Merged by: @BruceMacD

Base: mainHead: brucemacd/fix-arm-build


📝 Commits (1)

  • efc7757 fix ggml arm64 cuda build

📊 Changes

2 files changed (+35 additions, -2 deletions)

View changed files

📝 llm/llama.cpp/generate_linux.go (+3 -2)
llm/llama.cpp/ggml_patch/0005-ggml-support-CUDA-s-half-type-for-aarch64-1455-2670.patch (+32 -0)

📄 Description

Apply patch to support CUDA's half type for aarch64


🔄 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/520 **Author:** [@BruceMacD](https://github.com/BruceMacD) **Created:** 9/12/2023 **Status:** ✅ Merged **Merged:** 9/12/2023 **Merged by:** [@BruceMacD](https://github.com/BruceMacD) **Base:** `main` ← **Head:** `brucemacd/fix-arm-build` --- ### 📝 Commits (1) - [`efc7757`](https://github.com/ollama/ollama/commit/efc7757dfdaf177311092e69a7f5795d4ab46f96) fix ggml arm64 cuda build ### 📊 Changes **2 files changed** (+35 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `llm/llama.cpp/generate_linux.go` (+3 -2) ➕ `llm/llama.cpp/ggml_patch/0005-ggml-support-CUDA-s-half-type-for-aarch64-1455-2670.patch` (+32 -0) </details> ### 📄 Description Apply patch to support CUDA's half type for aarch64 --- <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 2026-04-19 15:13:34 -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#20735