From d8cea721ca6bf68e2b36535c9f3fe36d876579dc Mon Sep 17 00:00:00 2001 From: Justin Lee Date: Fri, 8 Nov 2024 10:30:36 -0800 Subject: [PATCH] elaborate on distributions --- docs/zero_to_hero_guide/quickstart.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/zero_to_hero_guide/quickstart.md b/docs/zero_to_hero_guide/quickstart.md index dbe724973..433083297 100644 --- a/docs/zero_to_hero_guide/quickstart.md +++ b/docs/zero_to_hero_guide/quickstart.md @@ -50,7 +50,7 @@ Follow the CLI prompts to complete the download. You may need to accept a licens ### 1. Build the Llama Stack Distribution -We will default into building a `meta-reference-gpu` distribution, however you could read more about the different distributions [here](https://llama-stack.readthedocs.io/en/latest/getting_started/index.html#decide-your-inference-provider). +We will default to building the `meta-reference-gpu` distribution due to its optimized configuration tailored for inference tasks that utilize local GPU capabilities effectively. If you have limited GPU resources, prefer using a cloud-based instance or plan to run on a CPU, you can explore other distribution options [here](https://llama-stack.readthedocs.io/en/latest/getting_started/index.html#decide-your-inference-provider). ```bash llama stack build --template meta-reference-gpu --image-type conda