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 #13317] [MERGED] CUDA: filter devices on secondary discovery #45410

New Issue
Closed
opened 2026-04-25 01:07:11 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-25 01:07:11 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/13317
Author: @dhiltgen
Created: 12/3/2025
Status: ✅ Merged
Merged: 12/3/2025
Merged by: @dhiltgen

Base: main ← Head: cuda_filter

📝 Commits (1)

  • 8137ffb CUDA: filter devices on secondary discovery

📊 Changes

3 files changed (+16 additions, -7 deletions)

View changed files

📝 discover/runner.go (+3 -2)
📝 llm/server.go (+1 -1)
📝 ml/device.go (+12 -4)

📄 Description

We now do a deeper probe of CUDA devices to verify the library version has the correct compute capability coverage for the device. Due to ROCm also interpreting the CUDA env var to filter AMD devices, we try to avoid setting it which leads to problems in mixed vendor systems. However without setting it for this deeper probe, each CUDA library subprocess discovers all CUDA GPUs and on systems with lots of GPUs, this can lead to hitting timeouts. The fix is to turn on the CUDA visibility env var just for this deeper probe use-case.

Fixes #13308

🔄 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/13317 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 12/3/2025 **Status:** ✅ Merged **Merged:** 12/3/2025 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `cuda_filter` --- ### 📝 Commits (1) - [`8137ffb`](https://github.com/ollama/ollama/commit/8137ffb516364c4a7567b9bff03c20888d2962a4) CUDA: filter devices on secondary discovery ### 📊 Changes **3 files changed** (+16 additions, -7 deletions) <details> <summary>View changed files</summary> 📝 `discover/runner.go` (+3 -2) 📝 `llm/server.go` (+1 -1) 📝 `ml/device.go` (+12 -4) </details> ### 📄 Description We now do a deeper probe of CUDA devices to verify the library version has the correct compute capability coverage for the device. Due to ROCm also interpreting the CUDA env var to filter AMD devices, we try to avoid setting it which leads to problems in mixed vendor systems. However without setting it for this deeper probe, each CUDA library subprocess discovers all CUDA GPUs and on systems with lots of GPUs, this can lead to hitting timeouts. The fix is to turn on the CUDA visibility env var just for this deeper probe use-case. Fixes #13308 --- <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 01:07:11 -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#45410
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?