[PR #11049] [MERGED] use nn.Linear in place of ml.Tensor #39295

Closed
opened 2026-04-22 23:57:25 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/11049
Author: @mxyng
Created: 6/11/2025
Status: Merged
Merged: 6/11/2025
Merged by: @mxyng

Base: mainHead: mxyng/moe


📝 Commits (1)

  • 7b0ba98 use nn.Linear in place of ml.Tensor

📊 Changes

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

View changed files

📝 model/models/llama4/model_text.go (+6 -6)
📝 model/models/qwen3/model.go (+6 -6)

📄 Description

while nn.Linear.Forward isn't applicable for sparse MLP, it's still a nice container for the tensors


🔄 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/11049 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 6/11/2025 **Status:** ✅ Merged **Merged:** 6/11/2025 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `mxyng/moe` --- ### 📝 Commits (1) - [`7b0ba98`](https://github.com/ollama/ollama/commit/7b0ba988d4ee323aa44ab516c45c119ab4c9e236) use nn.Linear in place of ml.Tensor ### 📊 Changes **2 files changed** (+12 additions, -12 deletions) <details> <summary>View changed files</summary> 📝 `model/models/llama4/model_text.go` (+6 -6) 📝 `model/models/qwen3/model.go` (+6 -6) </details> ### 📄 Description while nn.Linear.Forward isn't applicable for sparse MLP, it's still a nice container for the tensors --- <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 2026-04-22 23:57:25 -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#39295