feat(distro): no huggingface provider for starter (#3258)

The `trl` dependency brings in `accelerate` which brings in nvidia
dependencies for torch. We cannot have that in the starter distro. As
such, no CPU-only post-training for the huggingface provider.

llama_stack/distributions/ci-tests/build.yaml

@@ -34,7 +34,7 @@ distribution_spec:
     telemetry:
     - provider_type: inline::meta-reference
     post_training:
-    - provider_type: inline::huggingface-cpu
+    - provider_type: inline::torchtune-cpu
     eval:
     - provider_type: inline::meta-reference
     datasetio:

llama_stack/distributions/ci-tests/run.yaml

@@ -156,13 +156,10 @@ providers:
       sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/trace_store.db
       otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
   post_training:
-  - provider_id: huggingface-cpu
-    provider_type: inline::huggingface-cpu
+  - provider_id: torchtune-cpu
+    provider_type: inline::torchtune-cpu
     config:
-      checkpoint_format: huggingface
-      distributed_backend: null
-      device: cpu
-      dpo_output_dir: ~/.llama/distributions/ci-tests/dpo_output
+      checkpoint_format: meta
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/distributions/starter-gpu/build.yaml

@@ -35,7 +35,7 @@ distribution_spec:
     telemetry:
     - provider_type: inline::meta-reference
     post_training:
-    - provider_type: inline::torchtune-gpu
+    - provider_type: inline::huggingface-gpu
     eval:
     - provider_type: inline::meta-reference
     datasetio:

llama_stack/distributions/starter-gpu/run.yaml

@@ -156,10 +156,13 @@ providers:
       sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/trace_store.db
       otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
   post_training:
-  - provider_id: torchtune-gpu
-    provider_type: inline::torchtune-gpu
+  - provider_id: huggingface-gpu
+    provider_type: inline::huggingface-gpu
     config:
-      checkpoint_format: meta
+      checkpoint_format: huggingface
+      distributed_backend: null
+      device: cpu
+      dpo_output_dir: ~/.llama/distributions/starter-gpu/dpo_output
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/distributions/starter-gpu/starter_gpu.py

@@ -17,6 +17,6 @@ def get_distribution_template() -> DistributionTemplate:
     template.description = "Quick start template for running Llama Stack with several popular providers. This distribution is intended for GPU-enabled environments."
 
     template.providers["post_training"] = [
-        BuildProvider(provider_type="inline::torchtune-gpu"),
+        BuildProvider(provider_type="inline::huggingface-gpu"),
     ]
     return template

llama_stack/distributions/starter/build.yaml

@@ -35,7 +35,7 @@ distribution_spec:
     telemetry:
     - provider_type: inline::meta-reference
     post_training:
-    - provider_type: inline::huggingface-cpu
+    - provider_type: inline::torchtune-cpu
     eval:
     - provider_type: inline::meta-reference
     datasetio:

llama_stack/distributions/starter/run.yaml

@@ -156,13 +156,10 @@ providers:
       sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/trace_store.db
       otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
   post_training:
-  - provider_id: huggingface-cpu
-    provider_type: inline::huggingface-cpu
+  - provider_id: torchtune-cpu
+    provider_type: inline::torchtune-cpu
     config:
-      checkpoint_format: huggingface
-      distributed_backend: null
-      device: cpu
-      dpo_output_dir: ~/.llama/distributions/starter/dpo_output
+      checkpoint_format: meta
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference

llama_stack/distributions/starter/starter.py

@@ -120,7 +120,7 @@ def get_distribution_template() -> DistributionTemplate:
         ],
         "agents": [BuildProvider(provider_type="inline::meta-reference")],
         "telemetry": [BuildProvider(provider_type="inline::meta-reference")],
-        "post_training": [BuildProvider(provider_type="inline::huggingface-cpu")],
+        "post_training": [BuildProvider(provider_type="inline::torchtune-cpu")],
         "eval": [BuildProvider(provider_type="inline::meta-reference")],
         "datasetio": [
             BuildProvider(provider_type="remote::huggingface"),