[PR #11700] [MERGED] gptoss: fix memory calc #60304

Closed
opened 2026-04-29 15:13:51 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11700
Author: @mxyng
Created: 8/5/2025
Status: Merged
Merged: 8/5/2025
Merged by: @mxyng

Base: mainHead: mxyng/gpt-oss


📝 Commits (1)

📊 Changes

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

View changed files

📝 fs/ggml/ggml.go (+1 -1)

📄 Description

multipler was added by mistake so when model is offloaded to cpu, more gpu memory is thought to be used so even more layers will be offloaded


🔄 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/11700 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 8/5/2025 **Status:** ✅ Merged **Merged:** 8/5/2025 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `mxyng/gpt-oss` --- ### 📝 Commits (1) - [`2ee97d8`](https://github.com/ollama/ollama/commit/2ee97d802488e4d2809ea0a1085e22515be70db7) gptoss: fix memory calc ### 📊 Changes **1 file changed** (+1 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `fs/ggml/ggml.go` (+1 -1) </details> ### 📄 Description multipler was added by mistake so when model is offloaded to cpu, more gpu memory is thought to be used so even more layers will be offloaded --- <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 2026-04-29 15:13:51 -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#60304