phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 01:42:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore!: remove --image-type and --image-name from llama stack run (#3714)

Browse source 
# What does this PR do?
Simplifies the CLI. I don't think these options make sense anymore: only
venv is supported as image-type, and users can simply activate the env
before running `llama stack` as they do any other project.

## Test Plan





---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3714).
* __->__ #3714
* #3711
This commit is contained in:
ehhuang 2025-10-07 20:26:44 -07:00 • committed by GitHub
parent 372dedb3d6
commit 9b9ff3b9bb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 48 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

3
docs/zero_to_hero_guide/README.md
View file

@ -88,7 +88,7 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
...
Build Successful!
You can find the newly-built template here: ~/.llama/distributions/starter/starter-run.yaml
You can run the new Llama Stack Distro via: uv run --with llama-stack llama stack run starter --image-type venv
You can run the new Llama Stack Distro via: uv run --with llama-stack llama stack run starter
```
3. **Set the ENV variables by exporting them to the terminal**:
@ -106,7 +106,6 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
SAFETY_MODEL=$SAFETY_MODEL \
OLLAMA_URL=$OLLAMA_URL \
uv run --with llama-stack llama stack run starter \
--image-type venv \
--port $LLAMA_STACK_PORT
```
Note: Every time you run a new model with `ollama run`, you will need to restart the llama stack. Otherwise it won't see the new model.