github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #7217] [MERGED] Add arm64 cuda jetpack variants #43602

New Issue
Closed
opened 2026-04-24 23:12:42 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-24 23:12:42 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/7217
Author: @dhiltgen
Created: 10/15/2024
Status: ✅ Merged
Merged: 11/12/2024
Merged by: @dhiltgen

Base: main ← Head: go_server_jetson

📝 Commits (1)

  • ce1567a Jetpack support for Go server

📊 Changes

8 files changed (+78 additions, -20 deletions)

View changed files

📝 Dockerfile (+64 -8)
📝 discover/amd_linux.go (+1 -1)
📝 discover/amd_windows.go (+1 -1)
📝 discover/gpu.go (+4 -4)
📝 discover/types.go (+1 -1)
📝 llama/llama.go (+4 -2)
📝 llama/make/cuda.make (+1 -1)
📝 llm/server.go (+2 -2)

📄 Description

This adds 2 new variants for the arm64 build to support nvidia jetson systems based on jetpack 5 and 6. Jetpack 4 is too old to be built with our toolchain (the older cuda requires an old gcc which can't build llama.cpp) and will remain unsupported.

The sbsa discrete GPU cuda libraries we bundle in the existing arm64 build are incompatible with jetson iGPU systems. Unfortunately swapping them at runtime isn't viable given the way nvcc compilation/linking works, so we need to actually build and link against those specific cuda libraries, and bundle them.

File sizes are too large to try to combine into a single unified tgz bundle, so this splits things out into a main bundle which contains all the runners, and then two auxiliary bundles, one for jetpack 5 and 6 which contain all the libraries specific to those versions.

Fixes https://github.com/ollama/ollama/issues/2408
Fixes https://github.com/ollama/ollama/issues/4693
Fixes https://github.com/ollama/ollama/issues/5100
Fixes https://github.com/ollama/ollama/issues/4861
Fixes #6999
Fixes #7293

🔄 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/7217 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 10/15/2024 **Status:** ✅ Merged **Merged:** 11/12/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `go_server_jetson` --- ### 📝 Commits (1) - [`ce1567a`](https://github.com/ollama/ollama/commit/ce1567ae5d4197be34a964ae50b1233616af4476) Jetpack support for Go server ### 📊 Changes **8 files changed** (+78 additions, -20 deletions) <details> <summary>View changed files</summary> 📝 `Dockerfile` (+64 -8) 📝 `discover/amd_linux.go` (+1 -1) 📝 `discover/amd_windows.go` (+1 -1) 📝 `discover/gpu.go` (+4 -4) 📝 `discover/types.go` (+1 -1) 📝 `llama/llama.go` (+4 -2) 📝 `llama/make/cuda.make` (+1 -1) 📝 `llm/server.go` (+2 -2) </details> ### 📄 Description This adds 2 new variants for the arm64 build to support nvidia jetson systems based on jetpack 5 and 6. Jetpack 4 is too old to be built with our toolchain (the older cuda requires an old gcc which can't build llama.cpp) and will remain unsupported. The sbsa discrete GPU cuda libraries we bundle in the existing arm64 build are incompatible with jetson iGPU systems. Unfortunately swapping them at runtime isn't viable given the way nvcc compilation/linking works, so we need to actually build and link against those specific cuda libraries, and bundle them. File sizes are too large to try to combine into a single unified tgz bundle, so this splits things out into a main bundle which contains all the runners, and then two auxiliary bundles, one for jetpack 5 and 6 which contain all the libraries specific to those versions. Fixes https://github.com/ollama/ollama/issues/2408 Fixes https://github.com/ollama/ollama/issues/4693 Fixes https://github.com/ollama/ollama/issues/5100 Fixes https://github.com/ollama/ollama/issues/4861 Fixes #6999 Fixes #7293 --- <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 2026-04-24 23:12:42 -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#43602
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?