github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #10789] [MERGED] fix: qwen25vl assign samebatch in multimodal input #39240

New Issue
Closed
opened 2026-04-22 23:54:15 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 23:54:15 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/10789
Author: @mxyng
Created: 5/21/2025
Status: ✅ Merged
Merged: 5/21/2025
Merged by: @mxyng

Base: main ← Head: mxyng/fix-qwen25vl

📝 Commits (1)

  • 64fbec4 fix: qwen25vl assign samebatch in multimodal input

📊 Changes

1 file changed (+2 additions, -1 deletions)

View changed files

📝 model/models/qwen25vl/model.go (+2 -1)

📄 Description

setting samebatch on the vision start token is problematic because it will be shared with other inputs that also use images. this will cause the input to be cached and the runner will not see SameBatch. SameBatch will also be incorrect since it may be for a different image.

assigning samebatch to the input tokens resolves this by ensure it's assigned correctly to inputs corresponding to the image.

not setting same batch correctly may cause panics during inference since images are no longer guaranteed to be in the same 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/10789 **Author:** [@mxyng](https://github.com/mxyng) **Created:** 5/21/2025 **Status:** ✅ Merged **Merged:** 5/21/2025 **Merged by:** [@mxyng](https://github.com/mxyng) **Base:** `main` ← **Head:** `mxyng/fix-qwen25vl` --- ### 📝 Commits (1) - [`64fbec4`](https://github.com/ollama/ollama/commit/64fbec4bd85fd30f991fcf23d8e5a7b44d5f1c36) fix: qwen25vl assign samebatch in multimodal input ### 📊 Changes **1 file changed** (+2 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `model/models/qwen25vl/model.go` (+2 -1) </details> ### 📄 Description setting samebatch on the vision start token is problematic because it will be shared with other inputs that also use images. this will cause the input to be cached and the runner will not see SameBatch. SameBatch will also be incorrect since it may be for a different image. assigning samebatch to the input tokens resolves this by ensure it's assigned correctly to inputs corresponding to the image. not setting same batch correctly may cause panics during inference since images are no longer guaranteed to be in the same 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 2026-04-22 23:54:15 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#39240
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?