add inline-vllm details, fix things

distributions/inline-vllm/build.yaml

@@ -1 +1 @@
-../../llama_stack/templates/vllm/build.yaml
+../../llama_stack/templates/inline-vllm/build.yaml

distributions/inline-vllm/compose.yaml

@@ -0,0 +1,35 @@
+services:
+  llamastack:
+    image: llamastack/distribution-inline-vllm
+    network_mode: "host"
+    volumes:
+      - ~/.llama:/root/.llama
+      - ./run.yaml:/root/my-run.yaml
+    ports:
+      - "5000:5000"
+    devices:
+      - nvidia.com/gpu=all
+    environment:
+      - CUDA_VISIBLE_DEVICES=0
+    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
+    entrypoint: bash -c "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

distributions/inline-vllm/run.yaml

@@ -0,0 +1,66 @@
+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: vllm-inference
+    provider_type: inline::vllm
+    config:
+      model: Llama3.2-3B-Instruct
+      tensor_parallel_size: 1
+      gpu_memory_utilization: 0.4
+      enforce_eager: true
+      max_tokens: 4096
+  - provider_id: vllm-safety
+    provider_type: inline::vllm
+    config:
+      model: Llama-Guard-3-1B
+      tensor_parallel_size: 1
+      gpu_memory_utilization: 0.2
+      enforce_eager: true
+      max_tokens: 4096
+  safety:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config:
+      llama_guard_shield:
+        model: Llama-Guard-3-1B
+        excluded_categories: []
+# Uncomment to use prompt guard
+#      prompt_guard_shield:
+#        model: Prompt-Guard-86M
+  memory:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config: {}
+  # Uncomment to use pgvector
+  # - provider_id: pgvector
+  #   provider_type: remote::pgvector
+  #   config:
+  #     host: 127.0.0.1
+  #     port: 5432
+  #     db: postgres
+  #     user: postgres
+  #     password: mysecretpassword
+  agents:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: ~/.llama/runtime/agents_store.db
+  telemetry:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config: {}

distributions/remote-vllm/build.yaml

@@ -1 +1 @@
-../../llama_stack/templates/ollama/build.yaml
+../../llama_stack/templates/remote-vllm/build.yaml

distributions/remote-vllm/compose.yaml

@@ -1,11 +1,11 @@
 services:
-  ollama:
-    image: ollama/ollama:latest
+  vllm:
+    image: vllm/vllm-openai:latest
     network_mode: "host"
     volumes:
-      - ollama:/root/.ollama # this solution synchronizes with the docker volume and loads the model rocket fast
+      - $HOME/.cache/huggingface:/root/.cache/huggingface
     ports:
-      - "11434:11434"
+      - "8000:8000"
     devices:
       - nvidia.com/gpu=all
     environment:
@@ -27,17 +27,17 @@ services:
     runtime: nvidia
   llamastack:
     depends_on:
-    - ollama
-    image: llamastack/distribution-ollama
+    - vllm
+    image: llamastack/distribution-remote-vllm
     network_mode: "host"
     volumes:
       - ~/.llama:/root/.llama
       # Link to ollama run.yaml file
-      - ./run.yaml:/root/llamastack-run-ollama.yaml
+      - ./run.yaml:/root/llamastack-run-remote-vllm.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/llamastack-run-ollama.yaml"
+    # Hack: wait for vllm server to start before starting docker
+    entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-remote-vllm.yaml"
     deploy:
       restart_policy:
         condition: on-failure
@@ -45,4 +45,4 @@ services:
         max_attempts: 5
         window: 60s
 volumes:
-  ollama:
+  vllm:

distributions/remote-vllm/cpu/compose.yaml

@@ -1,30 +0,0 @@
-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/gpu/run.yaml

@@ -1,46 +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: 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: {}

distributions/remote-vllm/run.yaml

@@ -13,10 +13,10 @@ apis:
 - safety
 providers:
   inference:
-  - provider_id: ollama0
-    provider_type: remote::ollama
+  - provider_id: vllm0
+    provider_type: remote::vllm
     config:
-      url: http://127.0.0.1:14343
+      url: http://127.0.0.1:8000
   safety:
   - provider_id: meta0
     provider_type: meta-reference

llama_stack/providers/registry/inference.py

@@ -45,7 +45,7 @@ def available_providers() -> List[ProviderSpec]:
         ),
         InlineProviderSpec(
             api=Api.inference,
-            provider_type="vllm",
+            provider_type="inline::vllm",
             pip_packages=[
                 "vllm",
             ],

llama_stack/templates/inline-vllm/build.yaml

@@ -0,0 +1,13 @@
+name: meta-reference-gpu
+distribution_spec:
+  docker_image: pytorch/pytorch:2.5.0-cuda12.4-cudnn9-runtime
+  description: Use code from `llama_stack` itself to serve all llama stack APIs
+  providers:
+    inference: meta-reference
+    memory:
+    - meta-reference
+    - remote::chromadb
+    - remote::pgvector
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference

llama_stack/templates/remote-vllm/build.yaml

@@ -0,0 +1,12 @@
+name: remote-vllm
+distribution_spec:
+  description: Use (an external) vLLM server for running LLM inference
+  providers:
+    inference: remote::vllm
+    memory:
+    - meta-reference
+    - remote::chromadb
+    - remote::pgvector
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference

llama_stack/templates/vllm/build.yaml

@@ -1,9 +0,0 @@
-name: vllm
-distribution_spec:
-  description: Like local, but use vLLM for running LLM inference
-  providers:
-    inference: vllm
-    memory: meta-reference
-    safety: meta-reference
-    agents: meta-reference
-    telemetry: meta-reference