mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-18 19:02:30 +00:00
c8b5774ff3
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>
13 lines
451 B
Docker
13 lines
451 B
Docker
# Containerfile used to build our all in one ollama image to run tests in CI
|
|
# podman build --platform linux/amd64 -f Containerfile -t ollama-with-models .
|
|
#
|
|
FROM --platform=linux/amd64 ollama/ollama:latest
|
|
|
|
# Start ollama and pull models in a single layer
|
|
RUN ollama serve & \
|
|
sleep 5 && \
|
|
ollama pull llama3.2:3b-instruct-fp16 && \
|
|
ollama pull all-minilm:latest
|
|
|
|
# Set the entrypoint to start ollama serve
|
|
ENTRYPOINT ["ollama", "serve"]
|