github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #15608] api: expose GPU device info in /api/status #46476

New Issue
Open
opened 2026-04-25 01:53:43 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-25 01:53:43 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/15608
Author: @Frank-Schruefer
Created: 4/15/2026
Status: 🔄 Open

Base: main ← Head: feature/api-status-gpu-info

📝 Commits (2)

  • 132b47d sample: add segment-level repetition loop detection
  • 16d139b api: expose GPU device info in /api/status

📊 Changes

6 files changed (+240 additions, -24 deletions)

View changed files

📝 api/types.go (+31 -0)
📝 runner/ollamarunner/runner.go (+4 -0)
📝 sample/samplers.go (+86 -14)
📝 sample/samplers_benchmark_test.go (+4 -4)
📝 sample/samplers_test.go (+96 -6)
📝 server/routes.go (+19 -0)

📄 Description

Currently there is no way to query GPU hardware information through the Ollama API. This adds a Gpus field to StatusResponse that exposes available GPU devices via the existing discover.GPUDevices() function.

Clients can use this to query GPU hardware (name, total VRAM, compute capability, etc.) for capacity planning and model size selection — for example to determine the largest context window that still allows all model layers to be offloaded to the GPU, or to pick the largest model that fits in available VRAM.

The field is omitempty and fully backwards-compatible.

🔄 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/15608 **Author:** [@Frank-Schruefer](https://github.com/Frank-Schruefer) **Created:** 4/15/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `feature/api-status-gpu-info` --- ### 📝 Commits (2) - [`132b47d`](https://github.com/ollama/ollama/commit/132b47de13c7d839b536636c61a7c6f0380f4b24) sample: add segment-level repetition loop detection - [`16d139b`](https://github.com/ollama/ollama/commit/16d139b7d30167b7556f11d0f7c2f80b6d78dcda) api: expose GPU device info in /api/status ### 📊 Changes **6 files changed** (+240 additions, -24 deletions) <details> <summary>View changed files</summary> 📝 `api/types.go` (+31 -0) 📝 `runner/ollamarunner/runner.go` (+4 -0) 📝 `sample/samplers.go` (+86 -14) 📝 `sample/samplers_benchmark_test.go` (+4 -4) 📝 `sample/samplers_test.go` (+96 -6) 📝 `server/routes.go` (+19 -0) </details> ### 📄 Description Currently there is no way to query GPU hardware information through the Ollama API. This adds a `Gpus` field to `StatusResponse` that exposes available GPU devices via the existing `discover.GPUDevices()` function. Clients can use this to query GPU hardware (name, total VRAM, compute capability, etc.) for capacity planning and model size selection — for example to determine the largest context window that still allows all model layers to be offloaded to the GPU, or to pick the largest model that fits in available VRAM. The field is `omitempty` and fully backwards-compatible. --- <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 01:53:43 -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#46476
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?