github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #13654] [MERGED] docker: add missing deps #14317

New Issue
Closed
opened 2026-04-13 00:50:43 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-13 00:50:43 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/13654
Author: @dhiltgen
Created: 1/9/2026
Status: ✅ Merged
Merged: 1/9/2026
Merged by: @dhiltgen

Base: main ← Head: fix_docker

📝 Commits (1)

📊 Changes

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

View changed files

📝 Dockerfile (+1 -1)

📄 Description

The new MLX library has extra dependencies.

Verification using a temporary image I pushed with this change:

% docker run --rm -it --runtime=nvidia --gpus all -e LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/lib/ollama/mlx_cuda_v13/  --entrypoint /bin/imagegen dhiltgen/ollama:0.14.0-rc0-0-g33ee716-dirty --help
Usage of /bin/imagegen:
  -cfg-scale float
    	CFG scale for image editing (default 4)
  -cpuprofile string
    	Write CPU profile to file
  -gpu-capture string
    	Capture GPU trace to .gputrace file (run with MTL_CAPTURE_ENABLED=1)
  -height int
    	Image height (default 1024)
  -image string
    	Image path for multimodal models
  -input-image value
    	Input image for image editing (can be specified multiple times)
  -layer-cache
    	Enable layer caching for faster diffusion (Z-Image, Qwen-Image). Not compatible with CFG/negative prompts.
  -list
    	List tensors only
  -max-tokens int
    	Max tokens (default 100)
  -model string
    	Model directory
  -negative-prompt string
    	Negative prompt for CFG (empty = no CFG, matching Python)
  -output string
    	Output path (default "output.png")
  -prompt string
    	Prompt (default "Hello")
  -qwen-image
    	Qwen-Image text-to-image generation
  -qwen-image-edit
    	Qwen-Image-Edit image editing
  -seed int
    	Random seed (default 42)
  -steps int
    	Denoising steps (default 9)
  -temperature float
    	Temperature (default 0.7)
  -top-k int
    	Top-k sampling (default 40)
  -top-p float
    	Top-p sampling (default 0.9)
  -width int
    	Image width (default 1024)
  -wired-limit int
    	Metal wired memory limit in GB (default 32)
  -zimage
    	Z-Image generation

🔄 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/13654 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 1/9/2026 **Status:** ✅ Merged **Merged:** 1/9/2026 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `fix_docker` --- ### 📝 Commits (1) - [`769dcf5`](https://github.com/ollama/ollama/commit/769dcf5e4b6c8256fd25ba7d7d8dba8c9b40d8ec) docker: add missing deps ### 📊 Changes **1 file changed** (+1 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `Dockerfile` (+1 -1) </details> ### 📄 Description The new MLX library has extra dependencies. Verification using a temporary image I pushed with this change: ``` % docker run --rm -it --runtime=nvidia --gpus all -e LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/lib/ollama/mlx_cuda_v13/ --entrypoint /bin/imagegen dhiltgen/ollama:0.14.0-rc0-0-g33ee716-dirty --help Usage of /bin/imagegen: -cfg-scale float CFG scale for image editing (default 4) -cpuprofile string Write CPU profile to file -gpu-capture string Capture GPU trace to .gputrace file (run with MTL_CAPTURE_ENABLED=1) -height int Image height (default 1024) -image string Image path for multimodal models -input-image value Input image for image editing (can be specified multiple times) -layer-cache Enable layer caching for faster diffusion (Z-Image, Qwen-Image). Not compatible with CFG/negative prompts. -list List tensors only -max-tokens int Max tokens (default 100) -model string Model directory -negative-prompt string Negative prompt for CFG (empty = no CFG, matching Python) -output string Output path (default "output.png") -prompt string Prompt (default "Hello") -qwen-image Qwen-Image text-to-image generation -qwen-image-edit Qwen-Image-Edit image editing -seed int Random seed (default 42) -steps int Denoising steps (default 9) -temperature float Temperature (default 0.7) -top-k int Top-k sampling (default 40) -top-p float Top-p sampling (default 0.9) -width int Image width (default 1024) -wired-limit int Metal wired memory limit in GB (default 32) -zimage Z-Image generation ``` --- <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 2026-04-13 00:50:43 -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#14317
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?