rename

distributions/meta-reference-gpu/build.yaml

@@ -1,4 +1,4 @@
-name: meta-reference-gpu
+name: distribution-meta-reference-gpu
 distribution_spec:
   description: Use code from `llama_stack` itself to serve all llama stack APIs
   providers:

distributions/ollama/build.yaml

@@ -1,6 +1,6 @@
-name: local-ollama
+name: distribution-ollama
 distribution_spec:
-  description: Like local, but use ollama for running LLM inference
+  description: Use ollama for running LLM inference
   providers:
     inference: remote::ollama
     memory:

distributions/tgi/build.yaml

@@ -0,0 +1,13 @@
+name: distribution-tgi
+distribution_spec:
+  description: Use TGI for running LLM inference
+  providers:
+    inference: remote::tgi
+    memory:
+    - meta-reference
+    - remote::chromadb
+    - remote::pgvector
+    safety: meta-reference
+    agents: meta-reference
+    telemetry: meta-reference
+image_type: conda

llama_stack/cli/stack/build.py

@@ -13,7 +13,7 @@ from functools import lru_cache
 from pathlib import Path
 
 TEMPLATES_PATH = (
-    Path(os.path.relpath(__file__)).parent.parent.parent / "distribution" / "templates"
+    Path(os.path.relpath(__file__)).parent.parent.parent.parent / "distributions"
 )