github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11422] QWEN-VL vision encoder not on GPU #69600

New Issue
Open
opened 2026-05-04 18:36:47 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-04 18:36:47 -05:00
Owner
Copy Link

Originally created by @wangyi7099 on GitHub (Jul 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11422

What is the issue?

Before the first token is generated, GPU usage remains above 80%. After searching online, I found that the vision encoding phase (VIT) is running on the CPU instead of the GPU, which significantly slows down the generation of the first token. Is there a configuration parameter to make the model use the GPU during the vision encoding phase?

Relevant log output

OS

win11
No response

GPU

RTX4090
No response

CPU

No response

Ollama version

0.9.6
No response

Originally created by @wangyi7099 on GitHub (Jul 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11422 ### What is the issue? Before the first token is generated, GPU usage remains above 80%. After searching online, I found that the vision encoding phase (VIT) is running on the CPU instead of the GPU, which significantly slows down the generation of the first token. Is there a configuration parameter to make the model use the GPU during the vision encoding phase? ### Relevant log output ```shell ``` ### OS win11 _No response_ ### GPU RTX4090 _No response_ ### CPU _No response_ ### Ollama version 0.9.6 _No response_
GiteaMirror added the bug label 2026-05-04 18:36:47 -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 bug
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#69600
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?