github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.5k Packages Projects Releases 122 Wiki Activity

[PR #7674] [MERGED] build: fix arm container image #17754

New Issue
Closed
opened 2026-04-16 06:13:00 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-16 06:13:00 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/7674
Author: @dhiltgen
Created: 11/14/2024
Status: ✅ Merged
Merged: 11/15/2024
Merged by: @dhiltgen

Base: main ← Head: fix_arm_image

📝 Commits (1)

  • ca29a5d build: fix arm container image

📊 Changes

2 files changed (+6 additions, -7 deletions)

View changed files

📝 Dockerfile (+3 -7)
📝 docs/docker.md (+3 -0)

📄 Description

Fix a rebase glitch from the old C++ runner build model

Verified by inspection after building locally: (confirming the jetpack specific cuda libs are present, as well as the runners)

% docker run --rm -it --entrypoint bash dhiltgen/ollama:0.4.2-rc0-0-g4efb98c-dirty
root@1cc199483147:/# find lib/ollama/
lib/ollama/
lib/ollama/runners
lib/ollama/runners/cuda_v11
lib/ollama/runners/cuda_v11/ollama_llama_server
lib/ollama/runners/cuda_v12
lib/ollama/runners/cuda_v12/ollama_llama_server
lib/ollama/runners/cpu
lib/ollama/runners/cpu/ollama_llama_server
lib/ollama/runners/cuda_jetpack6
lib/ollama/runners/cuda_jetpack6/ollama_llama_server
lib/ollama/runners/cuda_jetpack5
lib/ollama/runners/cuda_jetpack5/ollama_llama_server
lib/ollama/libcublas.so.12.4.5.8
lib/ollama/libcudart.so.12.4.127
lib/ollama/libcublasLt.so.11
lib/ollama/libcudart.so.11.0
lib/ollama/libcublasLt.so.12.4.5.8
lib/ollama/libggml_cuda_v12.so
lib/ollama/libcudart.so.11.3.109
lib/ollama/libcublasLt.so
lib/ollama/libcublas.so.11.5.1.109
lib/ollama/libggml_cuda_v11.so
lib/ollama/libcudart.so
lib/ollama/libcublas.so
lib/ollama/libcublas.so.12
lib/ollama/libcublasLt.so.12
lib/ollama/libcudart.so.12
lib/ollama/libcublasLt.so.11.5.1.109
lib/ollama/libcublas.so.11
lib/ollama/cuda_jetpack6
lib/ollama/cuda_jetpack6/libcublasLt.so.12.2.5.6
lib/ollama/cuda_jetpack6/libcudart.so.12.2.140
lib/ollama/cuda_jetpack6/libcublasLt.so
lib/ollama/cuda_jetpack6/libcublas.so.12.2.5.6
lib/ollama/cuda_jetpack6/libcudart.so
lib/ollama/cuda_jetpack6/libcublas.so
lib/ollama/cuda_jetpack6/libcublas.so.12
lib/ollama/cuda_jetpack6/libcublasLt.so.12
lib/ollama/cuda_jetpack6/libcudart.so.12
lib/ollama/libggml_cuda_jetpack6.so
lib/ollama/cuda_jetpack5
lib/ollama/cuda_jetpack5/libcublasLt.so.11
lib/ollama/cuda_jetpack5/libcudart.so.11.0
lib/ollama/cuda_jetpack5/libcublas.so.11.6.6.84
lib/ollama/cuda_jetpack5/libcublasLt.so
lib/ollama/cuda_jetpack5/libcudart.so
lib/ollama/cuda_jetpack5/libcublas.so
lib/ollama/cuda_jetpack5/libcublasLt.so.11.6.6.84
lib/ollama/cuda_jetpack5/libcudart.so.11.4.298
lib/ollama/cuda_jetpack5/libcublas.so.11
lib/ollama/libggml_cuda_jetpack5.so

Also verified the image on a JetPack 5 Orin:

docker run --rm -it --runtime=nvidia -e OLLAMA_DEBUG=1 -e JETSON_JETPACK dhiltgen/ollama:0.4.2-rc0-1-gca3785d-dirty

# ollama run orca-mini --verbose hello
 Hello there! How can I assist you today?

total duration:       3.786969368s
load duration:        1.771817151s
prompt eval count:    42 token(s)
prompt eval duration: 1.245s
prompt eval rate:     33.73 tokens/s
eval count:           11 token(s)
eval duration:        767ms
eval rate:            14.34 tokens/s
# ollama ps
NAME                ID              SIZE      PROCESSOR    UNTIL
orca-mini:latest    2dbd9f439647    5.9 GB    100% GPU     4 minutes from now

🔄 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/7674 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 11/14/2024 **Status:** ✅ Merged **Merged:** 11/15/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `fix_arm_image` --- ### 📝 Commits (1) - [`ca29a5d`](https://github.com/ollama/ollama/commit/ca29a5da86b69198b4d6b14c0a5a77857e18aa4e) build: fix arm container image ### 📊 Changes **2 files changed** (+6 additions, -7 deletions) <details> <summary>View changed files</summary> 📝 `Dockerfile` (+3 -7) 📝 `docs/docker.md` (+3 -0) </details> ### 📄 Description Fix a rebase glitch from the old C++ runner build model Verified by inspection after building locally: (confirming the jetpack specific cuda libs are present, as well as the runners) ``` % docker run --rm -it --entrypoint bash dhiltgen/ollama:0.4.2-rc0-0-g4efb98c-dirty root@1cc199483147:/# find lib/ollama/ lib/ollama/ lib/ollama/runners lib/ollama/runners/cuda_v11 lib/ollama/runners/cuda_v11/ollama_llama_server lib/ollama/runners/cuda_v12 lib/ollama/runners/cuda_v12/ollama_llama_server lib/ollama/runners/cpu lib/ollama/runners/cpu/ollama_llama_server lib/ollama/runners/cuda_jetpack6 lib/ollama/runners/cuda_jetpack6/ollama_llama_server lib/ollama/runners/cuda_jetpack5 lib/ollama/runners/cuda_jetpack5/ollama_llama_server lib/ollama/libcublas.so.12.4.5.8 lib/ollama/libcudart.so.12.4.127 lib/ollama/libcublasLt.so.11 lib/ollama/libcudart.so.11.0 lib/ollama/libcublasLt.so.12.4.5.8 lib/ollama/libggml_cuda_v12.so lib/ollama/libcudart.so.11.3.109 lib/ollama/libcublasLt.so lib/ollama/libcublas.so.11.5.1.109 lib/ollama/libggml_cuda_v11.so lib/ollama/libcudart.so lib/ollama/libcublas.so lib/ollama/libcublas.so.12 lib/ollama/libcublasLt.so.12 lib/ollama/libcudart.so.12 lib/ollama/libcublasLt.so.11.5.1.109 lib/ollama/libcublas.so.11 lib/ollama/cuda_jetpack6 lib/ollama/cuda_jetpack6/libcublasLt.so.12.2.5.6 lib/ollama/cuda_jetpack6/libcudart.so.12.2.140 lib/ollama/cuda_jetpack6/libcublasLt.so lib/ollama/cuda_jetpack6/libcublas.so.12.2.5.6 lib/ollama/cuda_jetpack6/libcudart.so lib/ollama/cuda_jetpack6/libcublas.so lib/ollama/cuda_jetpack6/libcublas.so.12 lib/ollama/cuda_jetpack6/libcublasLt.so.12 lib/ollama/cuda_jetpack6/libcudart.so.12 lib/ollama/libggml_cuda_jetpack6.so lib/ollama/cuda_jetpack5 lib/ollama/cuda_jetpack5/libcublasLt.so.11 lib/ollama/cuda_jetpack5/libcudart.so.11.0 lib/ollama/cuda_jetpack5/libcublas.so.11.6.6.84 lib/ollama/cuda_jetpack5/libcublasLt.so lib/ollama/cuda_jetpack5/libcudart.so lib/ollama/cuda_jetpack5/libcublas.so lib/ollama/cuda_jetpack5/libcublasLt.so.11.6.6.84 lib/ollama/cuda_jetpack5/libcudart.so.11.4.298 lib/ollama/cuda_jetpack5/libcublas.so.11 lib/ollama/libggml_cuda_jetpack5.so ``` Also verified the image on a JetPack 5 Orin: ``` docker run --rm -it --runtime=nvidia -e OLLAMA_DEBUG=1 -e JETSON_JETPACK dhiltgen/ollama:0.4.2-rc0-1-gca3785d-dirty ``` ``` # ollama run orca-mini --verbose hello Hello there! How can I assist you today? total duration: 3.786969368s load duration: 1.771817151s prompt eval count: 42 token(s) prompt eval duration: 1.245s prompt eval rate: 33.73 tokens/s eval count: 11 token(s) eval duration: 767ms eval rate: 14.34 tokens/s # ollama ps NAME ID SIZE PROCESSOR UNTIL orca-mini:latest 2dbd9f439647 5.9 GB 100% GPU 4 minutes from now ``` --- <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 2026-04-16 06:13:00 -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#17754
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?