phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-25 21:57:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

ci: use ollama container image with loaded models

Browse source 
Instead of downloading the models each time we now have a single Ollama
container that is baked with the models pulled and ready to use.

This will remove the CI flakiness on model pulling.

Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-06-06 09:54:39 +02:00
parent 692709cd45
commit c8b5774ff3
No known key found for this signature in database
4 changed files with 29 additions and 194 deletions
Download patch file Download diff file Expand all files Collapse all files

5
.github/workflows/integration-tests.yml vendored
View file

@ -50,7 +50,7 @@ jobs:
env:
INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
run: |
LLAMA_STACK_LOG_FILE=server.log nohup uv run llama stack run ./llama_stack/templates/ollama/run.yaml --image-type venv &
LLAMA_STACK_LOG_FILE=server.log nohup uv run llama stack run ./llama_stack/templates/ollama/run.yaml --image-type venv --env OLLAMA_URL="http://0.0.0.0:11434" &
- name: Wait for Llama Stack server to be ready
if: matrix.client-type == 'http'
@ -87,6 +87,7 @@ jobs:
- name: Run Integration Tests
env:
INFERENCE_MODEL: "meta-llama/Llama-3.2-3B-Instruct"
OLLAMA_URL: "http://0.0.0.0:11434"
run: |
if [ "${{ matrix.client-type }}" == "library" ]; then
stack_config="ollama"
@ -107,7 +108,7 @@ jobs:
- name: Write ollama logs to file
if: ${{ always() }}
run: |
sudo journalctl -u ollama.service > ollama.log
sudo docker logs ollama > ollama.log
- name: Upload all logs to artifacts
if: ${{ always() }}