[PR #8113] [CLOSED] llama: add qwen2vl support #23166

Closed
opened 2026-04-19 16:48:29 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/8113
Author: @jmorganca
Created: 12/16/2024
Status: Closed

Base: mainHead: jmorganca/qwen2vl


📝 Commits (1)

  • 80d41b5 llama: add qwen2vl support

📊 Changes

5 files changed (+632 additions, -15 deletions)

View changed files

📝 llama/ggml-metal-embed.metal (+147 -0)
📝 llama/ggml-metal-impl.h (+1 -0)
📝 llama/ggml-metal.metal (+146 -0)
📝 llama/ggml-metal_darwin_arm64.m (+39 -15)
llama/patches/0014-qwen2vl-support.patch (+299 -0)

📄 Description

Still missing: add 4 positions per embedding when creating a batch


🔄 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/8113 **Author:** [@jmorganca](https://github.com/jmorganca) **Created:** 12/16/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `jmorganca/qwen2vl` --- ### 📝 Commits (1) - [`80d41b5`](https://github.com/ollama/ollama/commit/80d41b579b76fe2b10134e7e3fa0a184f6917e8d) llama: add qwen2vl support ### 📊 Changes **5 files changed** (+632 additions, -15 deletions) <details> <summary>View changed files</summary> 📝 `llama/ggml-metal-embed.metal` (+147 -0) 📝 `llama/ggml-metal-impl.h` (+1 -0) 📝 `llama/ggml-metal.metal` (+146 -0) 📝 `llama/ggml-metal_darwin_arm64.m` (+39 -15) ➕ `llama/patches/0014-qwen2vl-support.patch` (+299 -0) </details> ### 📄 Description Still missing: add 4 positions per embedding when creating a batch --- <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 16:48:29 -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#23166