add nvidia distribution (#565)

# What does this PR do?

adds nvidia template for creating a distribution using inference adapter
for NVIDIA NIMs.

## Test Plan

Please describe:
Build llama stack distribution for nvidia using the template, docker and
conda.
```bash
(.venv) local-cdgamarose@a4u8g-0006:~/llama-stack$ llama-stack-client configure --endpoint http://localhost:5000
Done! You can now use the Llama Stack Client CLI with endpoint http://localhost:5000
(.venv) local-cdgamarose@a4u8g-0006:~/llama-stack$ llama-stack-client models list
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ identifier                       ┃ provider_id ┃ provider_resource_id       ┃ metadata ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
│ Llama3.1-8B-Instruct             │ nvidia      │ meta/llama-3.1-8b-instruct │ {}       │
│ meta-llama/Llama-3.2-3B-Instruct │ nvidia      │ meta/llama-3.2-3b-instruct │ {}       │
└──────────────────────────────────┴─────────────┴────────────────────────────┴──────────┘
(.venv) local-cdgamarose@a4u8g-0006:~/llama-stack$ llama-stack-client inference chat-completion --message "hello, write me a 2 sentence poem"
ChatCompletionResponse(
    completion_message=CompletionMessage(
        content='Here is a 2 sentence poem:\n\nThe sun sets slow and paints the sky, \nA gentle hue of pink that makes me sigh.',
        role='assistant',
        stop_reason='end_of_turn',
        tool_calls=[]
    ),
    logprobs=None
)
```

## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] Ran pre-commit to handle lint / formatting issues.
- [x] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [x] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

---------

Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu>

distributions/inline-nvidia/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/nvidia/build.yaml

distributions/inline-nvidia/compose.yaml

@@ -0,0 +1,58 @@
+services:
+  nim:
+    image: ${DOCKER_IMAGE:-nvcr.io/nim/meta/llama-3.1-8b-instruct:latest}
+    network_mode: "host"
+    volumes:
+    - nim-llm-cache:/opt/nim/.cache
+    ports:
+      - "8000:8000"
+    shm_size: 16G
+    environment:
+      - CUDA_VISIBLE_DEVICES=0
+      - NIM_HTTP_API_PORT=8000
+      - NIM_TRITON_LOG_VERBOSE=1
+      - NGC_API_KEY=${NIM_NGC_API_KEY:-${NGC_API_KEY:-ngcapikey}}
+    command: []
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            # that's the closest analogue to --gpus; provide
+            # an integer amount of devices or 'all'
+            count: 1
+            # Devices are reserved using a list of capabilities, making
+            # capabilities the only required field. A device MUST
+            # satisfy all the requested capabilities for a successful
+            # reservation.
+            capabilities: [gpu]
+    runtime: nvidia
+    healthcheck:
+      test: ["CMD", "curl", "http://localhost:8000/v1/health/ready"]
+      interval: 5s
+      timeout: 5s
+      retries: 30
+      start_period: 120s
+  llamastack:
+    depends_on:
+    - nim
+    image: distribution-nvidia:dev
+    network_mode: "host"
+    volumes:
+      - ~/.llama:/root/.llama
+      - ./run.yaml:/root/llamastack-run-nvidia.yaml
+    ports:
+      - "5000:5000"
+    environment:
+      - INFERENCE_MODEL=${INFERENCE_MODEL:-Llama3.1-8B-Instruct}
+      - NVIDIA_API_KEY=${NVIDIA_API_KEY:-}
+    entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml-config /root/llamastack-run-nvidia.yaml"
+    deploy:
+      restart_policy:
+        condition: on-failure
+        delay: 3s
+        max_attempts: 5
+        window: 60s
+volumes:
+  nim-llm-cache:
+    driver: local

distributions/inline-nvidia/run.yaml

@@ -0,0 +1,100 @@
+version: '2'
+image_name: nvidia
+conda_env: nvidia
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- memory
+- safety
+- scoring
+- telemetry
+- tool_runtime
+providers:
+  inference:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      url: http://localhost:8000
+      api_key: ${env.NVIDIA_API_KEY} # TODO: don't need api key, code adjustments needed
+  memory:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/faiss_store.db
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config: {}
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence_store:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/agents_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config: {}
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config: {}
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config: {}
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+    config: {}
+  - provider_id: llm-as-judge
+    provider_type: inline::llm-as-judge
+    config: {}
+  - provider_id: braintrust
+    provider_type: inline::braintrust
+    config:
+      openai_api_key: ${env.OPENAI_API_KEY:}
+  tool_runtime:
+  - provider_id: brave-search
+    provider_type: remote::brave-search
+    config:
+      api_key: ${env.BRAVE_SEARCH_API_KEY:}
+      max_results: 3
+  - provider_id: tavily-search
+    provider_type: remote::tavily-search
+    config:
+      api_key: ${env.TAVILY_SEARCH_API_KEY:}
+      max_results: 3
+  - provider_id: code-interpreter
+    provider_type: inline::code-interpreter
+    config: {}
+  - provider_id: memory-runtime
+    provider_type: inline::memory-runtime
+    config: {}
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
+models:
+- metadata: {}
+  model_id: ${env.INFERENCE_MODEL}
+  provider_id: nvidia
+  model_type: llm
+shields: []
+memory_banks: []
+datasets: []
+scoring_fns: []
+eval_tasks: []
+tool_groups: []

distributions/remote-nvidia/build.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/nvidia/build.yaml

distributions/remote-nvidia/compose.yaml

@@ -0,0 +1,19 @@
+services:
+  llamastack:
+    image: distribution-nvidia:dev
+    network_mode: "host"
+    volumes:
+      - ~/.llama:/root/.llama
+      - ./run.yaml:/root/llamastack-run-nvidia.yaml
+    ports:
+      - "5000:5000"
+    environment:
+      - INFERENCE_MODEL=${INFERENCE_MODEL:-Llama3.1-8B-Instruct}
+      - NVIDIA_API_KEY=${NVIDIA_API_KEY:-}
+    entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml-config /root/llamastack-run-nvidia.yaml"
+    deploy:
+      restart_policy:
+        condition: on-failure
+        delay: 3s
+        max_attempts: 5
+        window: 60s

distributions/remote-nvidia/run.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/nvidia/run.yaml