diff --git a/benchmarking/k8s-benchmark/stack-configmap.yaml b/benchmarking/k8s-benchmark/stack-configmap.yaml index bf6109b68..286ba5f77 100644 --- a/benchmarking/k8s-benchmark/stack-configmap.yaml +++ b/benchmarking/k8s-benchmark/stack-configmap.yaml @@ -5,6 +5,7 @@ data: image_name: kubernetes-benchmark-demo apis: - agents + - files - inference - files - safety @@ -23,6 +24,14 @@ data: - provider_id: sentence-transformers provider_type: inline::sentence-transformers config: {} + files: + - provider_id: meta-reference-files + provider_type: inline::localfs + config: + storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files} + metadata_store: + type: sqlite + db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db vector_io: - provider_id: ${env.ENABLE_CHROMADB:+chromadb} provider_type: remote::chromadb diff --git a/benchmarking/k8s-benchmark/stack-k8s.yaml.template b/benchmarking/k8s-benchmark/stack-k8s.yaml.template index 9cb1e5be3..80867bac9 100644 --- a/benchmarking/k8s-benchmark/stack-k8s.yaml.template +++ b/benchmarking/k8s-benchmark/stack-k8s.yaml.template @@ -27,7 +27,7 @@ spec: spec: containers: - name: llama-stack-benchmark - image: llamastack/distribution-starter:latest + image: ehhuang/distribution-starter:latest imagePullPolicy: Always # since we have specified latest instead of a version env: - name: ENABLE_CHROMADB @@ -52,6 +52,8 @@ spec: value: http://vllm-server-safety.default.svc.cluster.local:8001/v1 - name: VLLM_TLS_VERIFY value: "false" + - name: LLAMA_STACK_LOGGING + value: "all=WARNING" command: ["python", "-m", "llama_stack.core.server.server", "/etc/config/stack_run_config.yaml", "--port", "8323"] ports: - containerPort: 8323