[PR #11349] [CLOSED] ggml: Support closing backends #75810

Closed
opened 2026-05-05 08:14:23 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11349
Author: @jessegross
Created: 7/9/2025
Status: Closed

Base: mainHead: jessegross/close


📝 Commits (1)

  • d602e1a ggml: Support closing backends

📊 Changes

4 files changed (+70 additions, -23 deletions)

View changed files

📝 ml/backend.go (+3 -0)
📝 ml/backend/ggml/ggml.go (+54 -23)
📝 runner/ollamarunner/cache.go (+4 -0)
📝 runner/ollamarunner/runner.go (+9 -0)

📄 Description

In order to iteratively find the best memory allocation, we need to be able to free backend memory so we can try again.


🔄 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/11349 **Author:** [@jessegross](https://github.com/jessegross) **Created:** 7/9/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `jessegross/close` --- ### 📝 Commits (1) - [`d602e1a`](https://github.com/ollama/ollama/commit/d602e1a823e3db020eda7373414e44d3b64bb11e) ggml: Support closing backends ### 📊 Changes **4 files changed** (+70 additions, -23 deletions) <details> <summary>View changed files</summary> 📝 `ml/backend.go` (+3 -0) 📝 `ml/backend/ggml/ggml.go` (+54 -23) 📝 `runner/ollamarunner/cache.go` (+4 -0) 📝 `runner/ollamarunner/runner.go` (+9 -0) </details> ### 📄 Description In order to iteratively find the best memory allocation, we need to be able to free backend memory so we can try again. --- <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 08:14:23 -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#75810