feat: re-work distro-codegen

each *.py file in the various templates now has to use `Provider`s rather than the stringified provider_types in the DistributionTemplate. Adjust that, regenerate all templates, docs, etc.

Signed-off-by: Charlie Doern <cdoern@redhat.com>

llama_stack/templates/nvidia/build.yaml

@@ -3,27 +3,39 @@ distribution_spec:
   description: Use NVIDIA NIM for running LLM inference, evaluation and safety
   providers:
     inference:
-    - remote::nvidia
+    - provider_id: nvidia
+      provider_type: remote::nvidia
     vector_io:
-    - inline::faiss
+    - provider_id: faiss
+      provider_type: inline::faiss
     safety:
-    - remote::nvidia
+    - provider_id: nvidia
+      provider_type: remote::nvidia
     agents:
-    - inline::meta-reference
+    - provider_id: meta-reference
+      provider_type: inline::meta-reference
     telemetry:
-    - inline::meta-reference
+    - provider_id: meta-reference
+      provider_type: inline::meta-reference
     eval:
-    - remote::nvidia
+    - provider_id: nvidia
+      provider_type: remote::nvidia
     post_training:
-    - remote::nvidia
+    - provider_id: nvidia
+      provider_type: remote::nvidia
     datasetio:
-    - inline::localfs
-    - remote::nvidia
+    - provider_id: localfs
+      provider_type: inline::localfs
+    - provider_id: nvidia
+      provider_type: remote::nvidia
     scoring:
-    - inline::basic
+    - provider_id: basic
+      provider_type: inline::basic
     tool_runtime:
-    - inline::rag-runtime
+    - provider_id: rag-runtime
+      provider_type: inline::rag-runtime
 image_type: conda
+image_name: nvidia
 additional_pip_packages:
 - aiosqlite
 - sqlalchemy[asyncio]

llama_stack/templates/nvidia/nvidia.py

@@ -17,16 +17,65 @@ from llama_stack.templates.template import DistributionTemplate, RunConfigSettin
 
 def get_distribution_template() -> DistributionTemplate:
     providers = {
-        "inference": ["remote::nvidia"],
-        "vector_io": ["inline::faiss"],
-        "safety": ["remote::nvidia"],
-        "agents": ["inline::meta-reference"],
-        "telemetry": ["inline::meta-reference"],
-        "eval": ["remote::nvidia"],
-        "post_training": ["remote::nvidia"],
-        "datasetio": ["inline::localfs", "remote::nvidia"],
-        "scoring": ["inline::basic"],
-        "tool_runtime": ["inline::rag-runtime"],
+        "inference": [
+            Provider(
+                provider_id="nvidia",
+                provider_type="remote::nvidia",
+            )
+        ],
+        "vector_io": [
+            Provider(
+                provider_id="faiss",
+                provider_type="inline::faiss",
+            )
+        ],
+        "safety": [
+            Provider(
+                provider_id="nvidia",
+                provider_type="remote::nvidia",
+            )
+        ],
+        "agents": [
+            Provider(
+                provider_id="meta-reference",
+                provider_type="inline::meta-reference",
+            )
+        ],
+        "telemetry": [
+            Provider(
+                provider_id="meta-reference",
+                provider_type="inline::meta-reference",
+            )
+        ],
+        "eval": [
+            Provider(
+                provider_id="nvidia",
+                provider_type="remote::nvidia",
+            )
+        ],
+        "post_training": [Provider(provider_id="nvidia", provider_type="remote::nvidia", config={})],
+        "datasetio": [
+            Provider(
+                provider_id="localfs",
+                provider_type="inline::localfs",
+            ),
+            Provider(
+                provider_id="nvidia",
+                provider_type="remote::nvidia",
+            ),
+        ],
+        "scoring": [
+            Provider(
+                provider_id="basic",
+                provider_type="inline::basic",
+            )
+        ],
+        "tool_runtime": [
+            Provider(
+                provider_id="rag-runtime",
+                provider_type="inline::rag-runtime",
+            )
+        ],
     }
 
     inference_provider = Provider(

llama_stack/templates/nvidia/run-with-safety.yaml

@@ -85,11 +85,9 @@ providers:
   scoring:
   - provider_id: basic
     provider_type: inline::basic
-    config: {}
   tool_runtime:
   - provider_id: rag-runtime
     provider_type: inline::rag-runtime
-    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db

llama_stack/templates/nvidia/run.yaml

@@ -74,11 +74,9 @@ providers:
   scoring:
   - provider_id: basic
     provider_type: inline::basic
-    config: {}
   tool_runtime:
   - provider_id: rag-runtime
     provider_type: inline::rag-runtime
-    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db