Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
docs: update suspend header in gpu.md (#8487)
EndoTheDev7bb356c6807c
diff --git a/docs/gpu.md b/docs/gpu.mdindex 691746d0d..399330026 100644--- a/docs/gpu.md+++ b/docs/gpu.md@@ -38,7 +38,7 @@ Numeric IDs may be used, however ordering may vary, so UUIDs are more reliable.You can discover the UUID of your GPUs by running `nvidia-smi -L` If you want toignore the GPUs and force CPU usage, use an invalid GPU ID (e.g., "-1")-### Laptop Suspend Resume+### Linux Suspend ResumeOn linux, after a suspend/resume cycle, sometimes Ollama will fail to discoveryour NVIDIA GPU, and fallback to running on the CPU. You can workaround this