Merge branch 'main' into inference_refactor

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -19,6 +19,9 @@ providers:
       model: ${env.INFERENCE_MODEL} # please make sure your inference model here is added as resource
       max_seq_len: 4096
       checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+    config: {}
   memory:
   - provider_id: faiss
     provider_type: inline::faiss
@@ -77,6 +80,13 @@ models: []
   model_id: ${env.INFERENCE_MODEL}
   provider_id: meta-reference-inference
   provider_model_id: null
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  provider_model_id: null
+  model_type: embedding
 shields: []
 memory_banks: []
 datasets: []