Docs for meta-reference-gpu

distributions/meta-reference-gpu/run.yaml

@@ -1,68 +1,56 @@
 version: '2'
-image_name: local
+image_name: meta-reference-gpu
 docker_image: null
-conda_env: local
+conda_env: null
 apis:
-- shields
 - agents
-- models
-- memory
-- memory_banks
 - inference
+- memory
 - safety
+- telemetry
 providers:
   inference:
-  - provider_id: inference0
+  - provider_id: meta-reference-inference
     provider_type: inline::meta-reference
     config:
-      model: Llama3.2-3B-Instruct
-      quantization: null
-      torch_seed: null
+      model: ${env.INFERENCE_MODEL}
       max_seq_len: 4096
-      max_batch_size: 1
-  - provider_id: inference1
-    provider_type: inline::meta-reference
-    config:
-      model: Llama-Guard-3-1B
-      quantization: null
-      torch_seed: null
-      max_seq_len: 2048
-      max_batch_size: 1
-  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
-# Uncomment to use prompt guard
-#      prompt_guard_shield:
-#        model: Prompt-Guard-86M
+      checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
   memory:
-  - provider_id: meta0
-    provider_type: inline::meta-reference
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/faiss_store.db
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
     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_id: meta-reference
     provider_type: inline::meta-reference
     config:
       persistence_store:
-        namespace: null
         type: sqlite
-        db_path: ~/.llama/runtime/agents_store.db
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/agents_store.db
   telemetry:
-  - provider_id: meta0
+  - provider_id: meta-reference
     provider_type: inline::meta-reference
     config: {}
+metadata_store:
+  namespace: null
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db
+models:
+- metadata: {}
+  model_id: ${env.INFERENCE_MODEL}
+  provider_id: meta-reference-inference
+  provider_model_id: null
+shields: []
+memory_banks: []
+datasets: []
+scoring_fns: []
+eval_tasks: []