[PR #13891] [MERGED] glm4moelite: quantize more tensors to 8-bit and avoid double BOS token #14433

Closed
opened 2026-04-13 00:53:57 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/13891
Author: @jmorganca
Created: 1/24/2026
Status: Merged
Merged: 1/25/2026
Merged by: @jmorganca

Base: mainHead: jmorganca/glm4moelite-fixes


📝 Commits (1)

  • c16ce2f glm4moelite: quantize more tensors to q8_0 and avoid double BOS token

📊 Changes

2 files changed (+8 additions, -1 deletions)

View changed files

📝 model/models/glm4moelite/model.go (+1 -1)
📝 server/quantization.go (+7 -0)

📄 Description

No description provided


🔄 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/13891 **Author:** [@jmorganca](https://github.com/jmorganca) **Created:** 1/24/2026 **Status:** ✅ Merged **Merged:** 1/25/2026 **Merged by:** [@jmorganca](https://github.com/jmorganca) **Base:** `main` ← **Head:** `jmorganca/glm4moelite-fixes` --- ### 📝 Commits (1) - [`c16ce2f`](https://github.com/ollama/ollama/commit/c16ce2f926ef08f60080fee8e340a84e9bc18608) glm4moelite: quantize more tensors to q8_0 and avoid double BOS token ### 📊 Changes **2 files changed** (+8 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `model/models/glm4moelite/model.go` (+1 -1) 📝 `server/quantization.go` (+7 -0) </details> ### 📄 Description _No description provided_ --- <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 2026-04-13 00:53:57 -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#14433