Add centml as remote inference provider

llama_stack/templates/centml/run.yaml

@@ -0,0 +1,129 @@
+version: '2'
+image_name: centml
+conda_env: centml
+apis:
+  - agents
+  - datasetio
+  - eval
+  - inference
+  - memory
+  - safety
+  - scoring
+  - telemetry
+  - tool_runtime
+providers:
+  inference:
+  - provider_id: centml
+    provider_type: remote::centml
+    config:
+      url: https://api.centml.com/openai/v1
+      api_key: "${env.CENTML_API_KEY}"
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+    config: {}
+
+  memory:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/centml}/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/centml}/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/centml}/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/centml}/registry.db
+
+models:
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: centml
+  provider_model_id: meta-llama/Llama-3.3-70B-Instruct
+  model_type: llm
+
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
+  provider_id: centml
+  provider_model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
+  model_type: llm
+
+shields:
+  - shield_id: meta-llama/Llama-Guard-3-8B
+
+memory_banks: []
+datasets: []
+scoring_fns: []
+eval_tasks: []
+tool_groups:
+  - toolgroup_id: builtin::websearch
+    provider_id: tavily-search
+  - toolgroup_id: builtin::memory
+    provider_id: memory-runtime
+  - toolgroup_id: builtin::code_interpreter
+    provider_id: code-interpreter