add docker template examples

llama_stack/distribution/templates/docker/llamastack-local-cpu/build.yaml

@@ -0,0 +1,15 @@
+name: local-cpu
+distribution_spec:
+  description: remote inference + local safety/agents/memory
+  docker_image: null
+  providers:
+    inference:
+    - remote::ollama
+    - remote::tgi
+    - remote::together
+    - remote::fireworks
+    safety: meta-reference
+    agents: meta-reference
+    memory: meta-reference
+    telemetry: meta-reference
+image_type: docker

llama_stack/distribution/templates/docker/llamastack-local-cpu/run.yaml

@@ -0,0 +1,64 @@
+built_at: '2024-09-30T09:04:30.533391'
+image_name: local-cpu
+docker_image: local-cpu
+conda_env: null
+apis_to_serve:
+- agents
+- inference
+- models
+- memory
+- safety
+- shields
+- memory_banks
+api_providers:
+  inference:
+    providers:
+    - remote::ollama
+  safety:
+    providers:
+    - meta-reference
+  agents:
+    provider_id: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: /home/xiyan/.llama/runtime/kvstore.db
+  memory:
+    providers:
+    - meta-reference
+  telemetry:
+    provider_id: meta-reference
+    config: {}
+routing_table:
+  inference:
+  - provider_id: remote::ollama
+    config:
+      host: localhost
+      port: 6000
+    routing_key: Meta-Llama3.1-8B-Instruct
+  safety:
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: llama_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: code_scanner_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: injection_shield
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: jailbreak_shield
+  memory:
+  - provider_id: meta-reference
+    config: {}
+    routing_key: vector

llama_stack/distribution/templates/docker/llamastack-local-gpu/Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.10-slim
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y        iputils-ping net-tools iproute2 dnsutils telnet        curl wget telnet        procps psmisc lsof        traceroute        bubblewrap        && rm -rf /var/lib/apt/lists/*
+
+RUN pip install /app/llama-stack-source
+RUN pip uninstall -y llama-models
+RUN pip install /app/llama-models-source
+
+RUN pip install fastapi fire httpx uvicorn accelerate blobfile fairscale fbgemm-gpu==0.8.0 torch torchvision transformers zmq codeshield transformers matplotlib pillow pandas scikit-learn aiosqlite psycopg2-binary redis blobfile chardet pypdf tqdm numpy scikit-learn scipy nltk sentencepiece transformers faiss-cpu
+RUN pip install torch --index-url https://download.pytorch.org/whl/cpu
+RUN pip install torch --index-url https://download.pytorch.org/whl/cpu
+RUN pip install sentence-transformers --no-deps
+
+# This would be good in production but for debugging flexibility lets not add it right now
+# We need a more solid production ready entrypoint.sh anyway
+#
+CMD ["python", "-m", "llama_stack.distribution.server.server", "./llamastack-run.yaml"]
+
+ADD tmp/configs/local-gpu-build.yaml ./llamastack-build.yaml
+ADD tmp/configs/local-gpu-run.yaml ./llamastack-run.yaml

llama_stack/distribution/templates/docker/llamastack-local-gpu/run.yaml

@@ -0,0 +1,67 @@
+built_at: '2024-09-30T09:00:56.693751'
+image_name: local-gpu
+docker_image: local-gpu
+conda_env: null
+apis_to_serve:
+- memory
+- inference
+- agents
+- shields
+- safety
+- models
+- memory_banks
+api_providers:
+  inference:
+    providers:
+    - meta-reference
+  safety:
+    providers:
+    - meta-reference
+  agents:
+    provider_id: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: /home/xiyan/.llama/runtime/kvstore.db
+  memory:
+    providers:
+    - meta-reference
+  telemetry:
+    provider_id: meta-reference
+    config: {}
+routing_table:
+  inference:
+  - provider_id: meta-reference
+    config:
+      model: Llama3.1-8B-Instruct
+      quantization: null
+      torch_seed: null
+      max_seq_len: 4096
+      max_batch_size: 1
+    routing_key: Llama3.1-8B-Instruct
+  safety:
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: llama_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: code_scanner_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: injection_shield
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: jailbreak_shield
+  memory:
+  - provider_id: meta-reference
+    config: {}
+    routing_key: vector