remote vllm distro

distributions/remote-vllm/cpu/compose.yaml

@@ -0,0 +1,30 @@
+services:
+  ollama:
+    image: ollama/ollama:latest
+    network_mode: "host"
+    volumes:
+      - ollama:/root/.ollama # this solution synchronizes with the docker volume and loads the model rocket fast
+    ports:
+      - "11434:11434"
+    command: []
+  llamastack:
+    depends_on:
+    - ollama
+    image: llamastack/distribution-ollama
+    network_mode: "host"
+    volumes:
+      - ~/.llama:/root/.llama
+      # Link to ollama run.yaml file
+      - ./run.yaml:/root/my-run.yaml
+    ports:
+      - "5000:5000"
+    # Hack: wait for ollama server to start before starting docker
+    entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
+    deploy:
+      restart_policy:
+        condition: on-failure
+        delay: 3s
+        max_attempts: 5
+        window: 60s
+volumes:
+  ollama:

distributions/remote-vllm/cpu/run.yaml

@@ -0,0 +1,46 @@
+version: '2'
+built_at: '2024-10-08T17:40:45.325529'
+image_name: local
+docker_image: null
+conda_env: local
+apis:
+- shields
+- agents
+- models
+- memory
+- memory_banks
+- inference
+- safety
+providers:
+  inference:
+  - provider_id: ollama0
+    provider_type: remote::ollama
+    config:
+      url: http://127.0.0.1:14343
+  safety:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config:
+      llama_guard_shield:
+        model: Llama-Guard-3-1B
+        excluded_categories: []
+        disable_input_check: false
+        disable_output_check: false
+      prompt_guard_shield:
+        model: Prompt-Guard-86M
+  memory:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config: {}
+  agents:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: ~/.llama/runtime/kvstore.db
+  telemetry:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config: {}