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 #12258] [CLOSED] cuda: require driver 550 or newer for compression #45005

New Issue
Closed
opened 2026-04-25 00:42:07 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-25 00:42:07 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/12258
Author: @dhiltgen
Created: 9/11/2025
Status: ❌ Closed

Base: main ← Head: min_driver_version

📝 Commits (1)

  • b998263 cuda: require driver 550 or newer for compression

📊 Changes

2 files changed (+6 additions, -1 deletions)

View changed files

📝 discover/gpu.go (+5 -0)
📝 docs/gpu.md (+1 -1)

📄 Description

Our minimum before was 531 (Feb 23) and this new min came out in Feb 24.

Without this changes, older drivers fail at runtime with errors like:

CUDA error: device kernel image is invalid
  current device: 0, in function ggml_cuda_mul_mat_q at //ml/backend/ggml/ggml/src/ggml-cuda/mmq.cu:129
  cudaGetLastError()
//ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:84: CUDA error

🔄 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/12258 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 9/11/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `min_driver_version` --- ### 📝 Commits (1) - [`b998263`](https://github.com/ollama/ollama/commit/b9982635ddd8dd00f13a6fd53f5e3f1848932f93) cuda: require driver 550 or newer for compression ### 📊 Changes **2 files changed** (+6 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `discover/gpu.go` (+5 -0) 📝 `docs/gpu.md` (+1 -1) </details> ### 📄 Description Our minimum before was 531 (Feb 23) and this new min came out in Feb 24. Without this changes, older drivers fail at runtime with errors like: ``` CUDA error: device kernel image is invalid current device: 0, in function ggml_cuda_mul_mat_q at //ml/backend/ggml/ggml/src/ggml-cuda/mmq.cu:129 cudaGetLastError() //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:84: CUDA error ``` --- <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 2026-04-25 00:42:07 -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#45005
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?