phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 06:23:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into docs-4

Browse source
This commit is contained in:
Francisco Arceo 2025-04-09 07:48:55 -06:00 • committed by GitHub
commit 3366937765
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
168 changed files with 14921 additions and 1625 deletions
Download patch file Download diff file Expand all files Collapse all files

12
docs/source/getting_started/index.md
View file

@ -12,17 +12,21 @@ as the inference [provider](../providers/index.md#inference) for a Llama Model.
## Step 1: Installation and Setup
### i. Install and Start Ollama for Inference
### i. Install and Setup Ollama for Inference
Install Ollama by following the instructions on the [Ollama website](https://ollama.com/download).
To start Ollama run:
Then download a Llama model with Ollama
```bash
ollama pull llama3.2:3b-instruct-fp16
```
This will instruct the Ollama service to download the Llama 3.2 3B Instruct model, which we'll use in the rest of this guide.
Then to start Ollama run:
```bash
ollama run llama3.2:3b --keepalive 60m
```
By default, Ollama keeps the model loaded in memory for 5 minutes which can be too short. We set the `--keepalive` flag to 60 minutes to ensure the model remains loaded for sometime.
### ii. Install `uv` to Manage your Python packages
Install [uv](https://docs.astral.sh/uv/) to setup your virtual environment