github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #1306] [CLOSED] Fix Docker image not using GPU #36417

New Issue
Closed
opened 2026-04-22 21:04:54 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 21:04:54 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/1306
Author: @bwest2397
Created: 11/28/2023
Status: ❌ Closed

Base: main ← Head: fix-docker-image-not-using-gpu

📝 Commits (2)

  • 7db4c93 Dockerfile: Use CUDA base image for final image
  • 30e87fe Use named stages in Dockerfile

📊 Changes

1 file changed (+3 additions, -3 deletions)

View changed files

📝 Dockerfile (+3 -3)

📄 Description

As it currently stands, the Docker image that gets built is seemingly unable to use the GPU despite the initial "build" stage of the Dockerfile ostensibly being built with CUDA support (i.e. built using the nvidia/cuda base image). As reported in https://github.com/jmorganca/ollama/issues/797, it seems that simply setting the second stage of the Dockerfile to use this same nvidia/cuda base image resolves the problem.

🔄 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/1306 **Author:** [@bwest2397](https://github.com/bwest2397) **Created:** 11/28/2023 **Status:** ❌ Closed **Base:** `main` ← **Head:** `fix-docker-image-not-using-gpu` --- ### 📝 Commits (2) - [`7db4c93`](https://github.com/ollama/ollama/commit/7db4c9382002bce3966424dcc6c2567e4c909844) Dockerfile: Use CUDA base image for final image - [`30e87fe`](https://github.com/ollama/ollama/commit/30e87fee44981a5a708173268568f9a4309559c3) Use named stages in Dockerfile ### 📊 Changes **1 file changed** (+3 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `Dockerfile` (+3 -3) </details> ### 📄 Description As it currently stands, the Docker image that gets built is seemingly unable to use the GPU despite the initial "build" stage of the Dockerfile ostensibly being built with CUDA support (i.e. built using the `nvidia/cuda` base image). As reported in https://github.com/jmorganca/ollama/issues/797, it seems that simply setting the second stage of the Dockerfile to use this same `nvidia/cuda` base image resolves the problem. --- <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 2026-04-22 21:04:54 -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#36417
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?