Compare commits

...

4 Commits

Author SHA1 Message Date
ParthSareen
7b152860c2 linter: remove prealloc 2025-12-01 15:36:16 -08:00
Daniel Hiltgen
467bbc0dd5 jetpack: require exact match or skip cuda_jetpack* (#13288)
The cuda_jetpack libs will enumerate discrete GPUs on SBSA systems
which leads to runtime failures of missing kernels.  This fix
requires an exact match to enable jetpacks instead of relying on
enumeration to filter out supported libraries.
2025-12-01 12:48:16 -08:00
Jeffrey Morgan
6d9f9323c5 .gitattributes: add app/webview to linguist-vendored (#13274) 2025-11-29 23:46:10 -05:00
Ondrej Kokes
0c2489605d docs: fix output formatting in faq.mdx (#13231)
There were a few Markdown typos in one FAQ answer. It now renders as a proper ascii table.
2025-11-28 19:19:21 -05:00
4 changed files with 13 additions and 4 deletions

2
.gitattributes vendored
View File

@@ -19,6 +19,8 @@ ml/backend/**/*.comp linguist-vendored
ml/backend/**/*.glsl linguist-vendored
ml/backend/**/CMakeLists.txt linguist-vendored
app/webview linguist-vendored
llama/build-info.cpp linguist-generated
ml/backend/ggml/ggml/src/ggml-metal/ggml-metal-embed.s linguist-generated

View File

@@ -23,7 +23,6 @@ linters:
- nolintlint
- nosprintfhostport
- perfsprint
- prealloc
- sloglint
- staticcheck
- unconvert

View File

@@ -98,6 +98,9 @@ func GPUDevices(ctx context.Context, runners []ml.FilteredRunnerDiscovery) []ml.
continue
} else if jetpack != "" && filepath.Base(dir) != "cuda_"+jetpack {
continue
} else if jetpack == "" && strings.Contains(filepath.Base(dir), "cuda_jetpack") {
slog.Debug("jetpack not detected (set JETSON_JETPACK or OLLAMA_LLM_LIBRARY to override), skipping", "libDir", dir)
continue
} else if !envconfig.EnableVulkan() && strings.Contains(filepath.Base(dir), "vulkan") {
slog.Info("experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1")
continue

View File

@@ -57,8 +57,13 @@ ollama ps
```
<Info>
**Output**: ``` NAME ID SIZE PROCESSOR UNTIL llama3:70b bcfb190ca3a7 42 GB
100% GPU 4 minutes from now ```
**Output**:
```
NAME ID SIZE PROCESSOR UNTIL
llama3:70b bcfb190ca3a7 42 GB 100% GPU 4 minutes from now
```
</Info>
The `Processor` column will show which memory the model was loaded in to:
@@ -385,4 +390,4 @@ Ollama for Windows and macOS register as a login item during installation. You
- In `Task Manager` go to the `Startup apps` tab, search for `ollama` then click `Disable`
**MacOS**
- Open `Settings` and search for "Login Items", find the `Ollama` entry under "Allow in the Background`, then click the slider to disable.
- Open `Settings` and search for "Login Items", find the `Ollama` entry under "Allow in the Background`, then click the slider to disable.