Merge pull request #1335 from rhatdan/llama-stack

llama stack run should be the CMD not run during build

Author: ericcurtin

container-images/llama-stack/Containerfile

@@ -3,17 +3,19 @@ FROM registry.fedoraproject.org/fedora:42
 # hack that should be removed when the following bug is addressed
 # https://github.com/containers/ramalama-stack/issues/53
 RUN curl --create-dirs --output ~/.llama/providers.d/remote/inference/ramalama.yaml https://raw.githubusercontent.com/containers/ramalama-stack/refs/tags/v0.1.3/src/ramalama_stack/providers.d/remote/inference/ramalama.yaml && \
-    curl --create-dirs --output ~/.llama/distributions/ramalama/ramalama-run.yaml https://raw.githubusercontent.com/containers/ramalama-stack/refs/tags/v0.1.3/src/ramalama_stack/ramalama-run.yaml
+    curl --create-dirs --output /etc/ramalama/ramalama-run.yaml https://raw.githubusercontent.com/containers/ramalama-stack/refs/tags/v0.1.3/src/ramalama_stack/ramalama-run.yaml
 
 RUN dnf -y update && \
     dnf -y install uv cmake gcc gcc-c++ python3-devel pkg-config sentencepiece-devel && \
     dnf -y clean all
 
-RUN uv venv  && \
-    uv pip install ramalama-stack && \
-    uv run llama stack run  --image-type venv --image-name /.venv ~/.llama/distributions/ramalama/ramalama-run.yaml
+RUN uv venv && \
+    uv pip install ramalama-stack
+
+ENV INFERENCE_MODEL=/mnt/model/model.file
 
 COPY --chmod=755 llama-stack/entrypoint.sh /usr/bin/entrypoint.sh
 
 ENTRYPOINT [ "/usr/bin/entrypoint.sh" ]
 
+CMD llama stack run --image-type venv /etc/ramalama/ramalama-run.yaml