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 #2131] [MERGED] Probe GPUs before backend init #21332

New Issue
Closed
opened 2026-04-19 15:35:01 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-19 15:35:01 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/2131
Author: @dhiltgen
Created: 1/21/2024
Status: ✅ Merged
Merged: 1/22/2024
Merged by: @dhiltgen

Base: main ← Head: probe_cards_at_init

📝 Commits (1)

  • ec37645 Probe GPUs before backend init

📊 Changes

1 file changed (+34 additions, -1 deletions)

View changed files

📝 llm/ext_server/ext_server.cpp (+34 -1)

📄 Description

Detect potential error scenarios so we can fallback to CPU mode without hitting asserts.

This won't fix the underlying errors we're seeing in #1940 and #1877 but it should hopefully allow us to detect the non-working scenario and fallback to CPU. We still need to understand why cudaGetDevice is failing on these systems (maybe incompatible cuda libs or drivers?)

🔄 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/2131 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 1/21/2024 **Status:** ✅ Merged **Merged:** 1/22/2024 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `probe_cards_at_init` --- ### 📝 Commits (1) - [`ec37645`](https://github.com/ollama/ollama/commit/ec3764538d4755448b326400093608040219fd5f) Probe GPUs before backend init ### 📊 Changes **1 file changed** (+34 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `llm/ext_server/ext_server.cpp` (+34 -1) </details> ### 📄 Description Detect potential error scenarios so we can fallback to CPU mode without hitting asserts. This won't fix the underlying errors we're seeing in #1940 and #1877 but it should hopefully allow us to detect the non-working scenario and fallback to CPU. We still need to understand why `cudaGetDevice` is failing on these systems (maybe incompatible cuda libs or drivers?) --- <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 2026-04-19 15:35:01 -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#21332
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?