github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7362] Llama3.2-vision image processing not implemented for /generate #30438

New Issue
Closed
opened 2026-04-22 10:03:33 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-22 10:03:33 -05:00
Owner
Copy Link

Originally created by @jessegross on GitHub (Oct 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7362

Originally assigned to: @pdevine on GitHub.

What is the issue?

Reported by @oderwat:
https://github.com/ollama/ollama/issues/6972#issuecomment-2437586368

OS

No response

GPU

No response

CPU

No response

Ollama version

0.4.0

Originally created by @jessegross on GitHub (Oct 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7362 Originally assigned to: @pdevine on GitHub. ### What is the issue? Reported by @oderwat: https://github.com/ollama/ollama/issues/6972#issuecomment-2437586368 ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.4.0
GiteaMirror added the bug label 2026-04-22 10:03:33 -05:00
GiteaMirror commented 2026-04-22 10:03:35 -05:00
Author
Owner
Copy Link

@chiehpower commented on GitHub (Oct 26, 2024):

Hi @jessegross

Could I confirm that currently only /api/chat is working properly, while /api/generate is not functioning as expected?

Thank you so much.

<!-- gh-comment-id:2439643651 --> @chiehpower commented on GitHub (Oct 26, 2024): Hi @jessegross Could I confirm that currently only `/api/chat` is working properly, while `/api/generate` is not functioning as expected? Thank you so much.
GiteaMirror commented 2026-04-22 10:03:35 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Oct 27, 2024):

@chiehpower that's correct. You can try PR #7384 to test out the /api/generate handler.

<!-- gh-comment-id:2440162339 --> @pdevine commented on GitHub (Oct 27, 2024): @chiehpower that's correct. You can try PR #7384 to test out the `/api/generate` handler.
GiteaMirror commented 2026-04-22 10:03:36 -05:00
Author
Owner
Copy Link

@chiehpower commented on GitHub (Oct 28, 2024):

Got it. Thank you so much!

<!-- gh-comment-id:2440259919 --> @chiehpower commented on GitHub (Oct 28, 2024): Got it. Thank you so much!
GiteaMirror commented 2026-04-22 10:03:36 -05:00
Author
Owner
Copy Link

@oderwat commented on GitHub (Oct 28, 2024):

This was merged into "main", and when compiling main this does not work for me when using 'llama-3.2-vision' neither with chat nor with generate.

key clip.has_text_encoder not found in file
terminate called after throwing an instance of 'std::runtime_error'
  what():  Missing required key: clip.has_text_encoder

I believe that this needs to be merged with v0.4.0-rc5 and get a v0.4.0-r6 to be useable or is the plan to rebase the v0.4.0 code and then create the new release candidate for v0.4.0?

Or did I understand something wrong?

<!-- gh-comment-id:2442677663 --> @oderwat commented on GitHub (Oct 28, 2024): This was merged into "main", and when compiling main this does not work for me when using 'llama-3.2-vision' neither with chat nor with generate. ``` key clip.has_text_encoder not found in file terminate called after throwing an instance of 'std::runtime_error' what(): Missing required key: clip.has_text_encoder ``` I believe that this needs to be merged with v0.4.0-rc5 and get a v0.4.0-r6 to be useable or is the plan to rebase the v0.4.0 code and then create the new release candidate for v0.4.0? Or did I understand something wrong?
GiteaMirror commented 2026-04-22 10:03:37 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Oct 28, 2024):

You need to build according to the instructions here in order to support llama3.2-vision:
https://github.com/ollama/ollama/blob/main/docs/development.md#transition-to-go-runner

<!-- gh-comment-id:2442849451 --> @jessegross commented on GitHub (Oct 28, 2024): You need to build according to the instructions here in order to support llama3.2-vision: https://github.com/ollama/ollama/blob/main/docs/development.md#transition-to-go-runner
GiteaMirror commented 2026-04-22 10:03:38 -05:00
Author
Owner
Copy Link

@oderwat commented on GitHub (Oct 28, 2024):

@jessegross thank you!

For reference: I am on WSL2 with RTX 3090 TI, and it builds (and uses CUDA) with this build script:

#!/bin/bash
echo "Setting limit higher for mlock to work"
limit=8413752832
sudo prlimit --memlock=$limit:$limit --pid $$

git fetch
git checkout main
export LIBRARY_PATH=/usr/lib/wsl/lib
make -C llama -j 4
go build .
# run it for unlimited use in my private network
OLLAMA_HOST=0.0.0.0:11434 OLLAMA_ORIGINS="*" ./ollama serve
<!-- gh-comment-id:2442862378 --> @oderwat commented on GitHub (Oct 28, 2024): @jessegross thank you! For reference: I am on WSL2 with RTX 3090 TI, and it builds (and uses CUDA) with this build script: ``` #!/bin/bash echo "Setting limit higher for mlock to work" limit=8413752832 sudo prlimit --memlock=$limit:$limit --pid $$ git fetch git checkout main export LIBRARY_PATH=/usr/lib/wsl/lib make -C llama -j 4 go build . # run it for unlimited use in my private network OLLAMA_HOST=0.0.0.0:11434 OLLAMA_ORIGINS="*" ./ollama serve ```
GiteaMirror commented 2026-04-22 10:03:38 -05:00
Author
Owner
Copy Link

@oderwat commented on GitHub (Oct 28, 2024):

Using this I could update my capollama to use the generate API 👍

<!-- gh-comment-id:2442866184 --> @oderwat commented on GitHub (Oct 28, 2024): Using this I could update my [capollama](https://github.com/oderwat/capollama) to use the generate API 👍
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#30438
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?