[PR #12526] [MERGED] Qwen3VL Cloud Parser and Renderer #24399

Closed
opened 2026-04-19 17:33:17 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12526
Author: @gr4ceG
Created: 10/7/2025
Status: Merged
Merged: 10/13/2025
Merged by: @gr4ceG

Base: mainHead: grace/qwen3-vl-renderer


📝 Commits (10+)

  • 0da3def working (other than tool call is the incorrect order) for tool calls and tools
  • 01599d0 Qwen3VL tests
  • ad41f82 Tests work, other than image tags (tests do not go through server) and tools (not in the correct order, but contents are the same)
  • 544dcfa testing for qwen3vl parser - toolparser is working
  • e68b03a working tests, changed code to find the first open tag
  • cd4e6af restore qwen3coder
  • 1aed777 clean up the renderer
  • 581fd44 made changes to JSON tool parser, wraps the TollCallFunction with a TollCall object
  • e44c128 changed image/video renderer
  • babf415 comment cleanup

📊 Changes

16 files changed (+2654 additions, -22 deletions)

View changed files

📝 api/types.go (+3 -3)
📝 model/parsers/parsers.go (+3 -0)
📝 model/parsers/qwen3coder.go (+3 -1)
📝 model/parsers/qwen3coder_test.go (+15 -0)
model/parsers/qwen3vl.go (+228 -0)
model/parsers/qwen3vl_nonthinking_test.go (+655 -0)
model/parsers/qwen3vl_thinking_test.go (+346 -0)
📝 model/renderers/qwen3coder.go (+3 -1)
📝 model/renderers/qwen3coder_test.go (+1 -1)
model/renderers/qwen3vl.go (+166 -0)
model/renderers/qwen3vl_nonthinking_test.go (+497 -0)
model/renderers/qwen3vl_test.go (+346 -0)
model/renderers/qwen3vl_thinking_test.go (+372 -0)
📝 model/renderers/renderer.go (+9 -15)
📝 openai/openai.go (+5 -0)
📝 server/prompt.go (+2 -1)

📄 Description

Adding parser and renderer for Qwen3VL on cloud.


🔄 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/12526 **Author:** [@gr4ceG](https://github.com/gr4ceG) **Created:** 10/7/2025 **Status:** ✅ Merged **Merged:** 10/13/2025 **Merged by:** [@gr4ceG](https://github.com/gr4ceG) **Base:** `main` ← **Head:** `grace/qwen3-vl-renderer` --- ### 📝 Commits (10+) - [`0da3def`](https://github.com/ollama/ollama/commit/0da3def9f2d55c33196c709f0dcd055090bfd232) working (other than tool call is the incorrect order) for tool calls and tools - [`01599d0`](https://github.com/ollama/ollama/commit/01599d0fefa8a96fd462dee2c5ced6728d590ee9) Qwen3VL tests - [`ad41f82`](https://github.com/ollama/ollama/commit/ad41f8241ac927887fce6dc335dced3dd164cdc7) Tests work, other than image tags (tests do not go through server) and tools (not in the correct order, but contents are the same) - [`544dcfa`](https://github.com/ollama/ollama/commit/544dcfa4ee39999b79e6cf9b80268ddd6f088d01) testing for qwen3vl parser - toolparser is working - [`e68b03a`](https://github.com/ollama/ollama/commit/e68b03a5aabe47f838da49a922f67dfa0373bf5f) working tests, changed code to find the first open tag - [`cd4e6af`](https://github.com/ollama/ollama/commit/cd4e6af4bb640a33bc2d17ca4377341ed94580c7) restore qwen3coder - [`1aed777`](https://github.com/ollama/ollama/commit/1aed77700643acfb3bb68b5c60284afc22fbf425) clean up the renderer - [`581fd44`](https://github.com/ollama/ollama/commit/581fd44b2bee0f31d8dbb1d8a48df276c030f88f) made changes to JSON tool parser, wraps the TollCallFunction with a TollCall object - [`e44c128`](https://github.com/ollama/ollama/commit/e44c12869248a69c1f887c778cae6d7a014d841c) changed image/video renderer - [`babf415`](https://github.com/ollama/ollama/commit/babf4152281323fe5c23e965ad49bb8bc837719c) comment cleanup ### 📊 Changes **16 files changed** (+2654 additions, -22 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+3 -3) 📝 `model/parsers/parsers.go` (+3 -0) 📝 `model/parsers/qwen3coder.go` (+3 -1) 📝 `model/parsers/qwen3coder_test.go` (+15 -0) ➕ `model/parsers/qwen3vl.go` (+228 -0) ➕ `model/parsers/qwen3vl_nonthinking_test.go` (+655 -0) ➕ `model/parsers/qwen3vl_thinking_test.go` (+346 -0) 📝 `model/renderers/qwen3coder.go` (+3 -1) 📝 `model/renderers/qwen3coder_test.go` (+1 -1) ➕ `model/renderers/qwen3vl.go` (+166 -0) ➕ `model/renderers/qwen3vl_nonthinking_test.go` (+497 -0) ➕ `model/renderers/qwen3vl_test.go` (+346 -0) ➕ `model/renderers/qwen3vl_thinking_test.go` (+372 -0) 📝 `model/renderers/renderer.go` (+9 -15) 📝 `openai/openai.go` (+5 -0) 📝 `server/prompt.go` (+2 -1) </details> ### 📄 Description Adding parser and renderer for Qwen3VL on cloud. --- <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 17:33:17 -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#24399