Auto-generate distro yamls + docs (#468)

# What does this PR do?

Automatically generates
- build.yaml
- run.yaml
- run-with-safety.yaml
- parts of markdown docs

for the distributions.

## Test Plan

At this point, this only updates the YAMLs and the docs. Some testing
(especially with ollama and vllm) has been performed but needs to be
much more tested.

distributions/tgi/compose.yaml

@@ -1,51 +1,89 @@
 services:
-  text-generation-inference:
+  tgi-inference:
     image: ghcr.io/huggingface/text-generation-inference:latest
-    network_mode: "host"
     volumes:
       - $HOME/.cache/huggingface:/data
+    network_mode: ${NETWORK_MODE:-bridged}
     ports:
-      - "5009:5009"
+       - "${TGI_INFERENCE_PORT:-8080}:${TGI_INFERENCE_PORT:-8080}"
     devices:
       - nvidia.com/gpu=all
     environment:
-      - CUDA_VISIBLE_DEVICES=0
+      - CUDA_VISIBLE_DEVICES=${TGI_INFERENCE_GPU:-0}
+      - HF_TOKEN=$HF_TOKEN
       - HF_HOME=/data
       - HF_DATASETS_CACHE=/data
       - HF_MODULES_CACHE=/data
       - HF_HUB_CACHE=/data
-    command: ["--dtype", "bfloat16", "--usage-stats", "on", "--sharded", "false", "--model-id", "meta-llama/Llama-3.1-8B-Instruct", "--port", "5009", "--cuda-memory-fraction", "0.3"]
+    command: >
+      --dtype bfloat16
+      --usage-stats off
+      --sharded false
+      --model-id ${TGI_INFERENCE_MODEL:-meta-llama/Llama-3.2-3B-Instruct}
+      --port ${TGI_INFERENCE_PORT:-8080}
+      --cuda-memory-fraction 0.75
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://tgi-inference:${TGI_INFERENCE_PORT:-8080}/health"]
+      interval: 5s
+      timeout: 5s
+      retries: 30
     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
+
+  tgi-${TGI_SAFETY_MODEL:+safety}:
+    image: ghcr.io/huggingface/text-generation-inference:latest
+    volumes:
+      - $HOME/.cache/huggingface:/data
+    network_mode: ${NETWORK_MODE:-bridged}
+    ports:
+       - "${TGI_SAFETY_PORT:-8081}:${TGI_SAFETY_PORT:-8081}"
+    devices:
+      - nvidia.com/gpu=all
+    environment:
+      - CUDA_VISIBLE_DEVICES=${TGI_SAFETY_GPU:-1}
+      - HF_TOKEN=$HF_TOKEN
+      - HF_HOME=/data
+      - HF_DATASETS_CACHE=/data
+      - HF_MODULES_CACHE=/data
+      - HF_HUB_CACHE=/data
+    command: >
+      --dtype bfloat16
+      --usage-stats off
+      --sharded false
+      --model-id ${TGI_SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
+      --port ${TGI_SAFETY_PORT:-8081}
+      --cuda-memory-fraction 0.75
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://text-generation-inference:5009/health"]
+      test: ["CMD", "curl", "-f", "http://tgi-safety:${TGI_SAFETY_PORT:-8081}/health"]
       interval: 5s
       timeout: 5s
       retries: 30
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            capabilities: [gpu]
+    runtime: nvidia
+
   llamastack:
     depends_on:
-      text-generation-inference:
+      tgi-inference:
         condition: service_healthy
-    image: llamastack/distribution-tgi
-    network_mode: "host"
+      tgi-${TGI_SAFETY_MODEL:+safety}:
+        condition: service_healthy
+    image: llamastack/distribution-tgi:test-0.0.52rc3
+    network_mode: ${NETWORK_MODE:-bridged}
     volumes:
       - ~/.llama:/root/.llama
-      # Link to TGI run.yaml file
-      - ./run.yaml:/root/my-run.yaml
+      - ./run${TGI_SAFETY_MODEL:+-with-safety}.yaml:/root/my-run.yaml
     ports:
-      - "5000:5000"
+      - "${LLAMA_STACK_PORT:-5001}:${LLAMA_STACK_PORT:-5001}"
     # Hack: wait for TGI server to start before starting docker
     entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
     restart_policy:
@@ -53,3 +91,13 @@ services:
       delay: 3s
       max_attempts: 5
       window: 60s
+    environment:
+      - TGI_URL=http://tgi-inference:${TGI_INFERENCE_PORT:-8080}
+      - SAFETY_TGI_URL=http://tgi-safety:${TGI_SAFETY_PORT:-8081}
+      - INFERENCE_MODEL=${INFERENCE_MODEL:-meta-llama/Llama-3.2-3B-Instruct}
+      - SAFETY_MODEL=${SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
+
+volumes:
+  tgi-inference:
+  tgi-safety:
+  llamastack:

distributions/tgi/run-with-safety.yaml

@@ -0,0 +1 @@
+../../llama_stack/templates/tgi/run-with-safety.yaml

distributions/tgi/run.yaml

@@ -1,45 +0,0 @@
-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: tgi0
-    provider_type: remote::tgi
-    config:
-      url: http://127.0.0.1:5009
-  safety:
-  - provider_id: meta0
-    provider_type: inline::llama-guard
-    config:
-      model: Llama-Guard-3-1B
-      excluded_categories: []
-  - provider_id: meta1
-    provider_type: inline::prompt-guard
-    config:
-      model: Prompt-Guard-86M
-  memory:
-  - provider_id: meta0
-    provider_type: inline::meta-reference
-    config: {}
-  agents:
-  - provider_id: meta0
-    provider_type: inline::meta-reference
-    config:
-      persistence_store:
-        namespace: null
-        type: sqlite
-        db_path: ~/.llama/runtime/kvstore.db
-  telemetry:
-  - provider_id: meta0
-    provider_type: inline::meta-reference
-    config: {}

distributions/tgi/run.yaml

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