Rename all inline providers with an inline:: prefix (#423)

distributions/bedrock/run.yaml

@@ -23,7 +23,7 @@ providers:
         region_name: <AWS_REGION>
   memory:
     - provider_id: meta0
-      provider_type: meta-reference
+      provider_type: inline::meta-reference
       config: {}
   safety:
     - provider_id: bedrock0
@@ -35,12 +35,12 @@ providers:
         region_name: <AWS_REGION>
   agents:
     - provider_id: meta0
-      provider_type: meta-reference
+      provider_type: inline::meta-reference
       config:
         persistence_store:
           type: sqlite
           db_path: ~/.llama/runtime/kvstore.db
   telemetry:
     - provider_id: meta0
-      provider_type: meta-reference
+      provider_type: inline::meta-reference
       config: {}

distributions/dell-tgi/run.yaml

@@ -29,11 +29,11 @@ providers:
       model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -41,5 +41,5 @@ providers:
         db_path: ~/.llama/runtime/kvstore.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

distributions/fireworks/run.yaml

@@ -31,7 +31,7 @@ providers:
       model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}
   # Uncomment to use weaviate memory provider
   # - provider_id: weaviate0
@@ -39,7 +39,7 @@ providers:
   #   config: {}
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -47,5 +47,5 @@ providers:
         db_path: ~/.llama/runtime/kvstore.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

distributions/inline-vllm/run.yaml

@@ -42,7 +42,7 @@ providers:
   #     model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}
   # Uncomment to use pgvector
   # - provider_id: pgvector
@@ -55,7 +55,7 @@ providers:
   #     password: mysecretpassword
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -63,5 +63,5 @@ providers:
         db_path: ~/.llama/runtime/agents_store.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

distributions/meta-reference-gpu/run.yaml

@@ -14,7 +14,7 @@ apis:
 providers:
   inference:
   - provider_id: inference0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       model: Llama3.2-3B-Instruct
       quantization: null
@@ -22,7 +22,7 @@ providers:
       max_seq_len: 4096
       max_batch_size: 1
   - provider_id: inference1
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       model: Llama-Guard-3-1B
       quantization: null
@@ -44,7 +44,7 @@ providers:
 #        model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}
   # Uncomment to use pgvector
   # - provider_id: pgvector
@@ -57,7 +57,7 @@ providers:
   #     password: mysecretpassword
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -65,5 +65,5 @@ providers:
         db_path: ~/.llama/runtime/agents_store.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

distributions/meta-reference-quantized-gpu/run.yaml

@@ -14,7 +14,7 @@ apis:
 providers:
   inference:
   - provider_id: meta0
-    provider_type: meta-reference-quantized
+    provider_type: inline::meta-reference-quantized
     config:
       model: Llama3.2-3B-Instruct:int4-qlora-eo8
       quantization:
@@ -23,7 +23,7 @@ providers:
       max_seq_len: 2048
       max_batch_size: 1
   - provider_id: meta1
-    provider_type: meta-reference-quantized
+    provider_type: inline::meta-reference-quantized
     config:
       # not a quantized model !
       model: Llama-Guard-3-1B
@@ -43,11 +43,11 @@ providers:
       model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -55,5 +55,5 @@ providers:
         db_path: ~/.llama/runtime/kvstore.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

distributions/ollama-gpu/run.yaml

@@ -29,11 +29,11 @@ providers:
       model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -41,5 +41,5 @@ providers:
         db_path: ~/.llama/runtime/kvstore.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

distributions/ollama/run.yaml

@@ -29,11 +29,11 @@ providers:
       model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -41,5 +41,5 @@ providers:
         db_path: ~/.llama/runtime/kvstore.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

distributions/remote-vllm/run.yaml

@@ -29,11 +29,11 @@ providers:
       model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -41,5 +41,5 @@ providers:
         db_path: ~/.llama/runtime/kvstore.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

distributions/tgi/run.yaml

@@ -29,11 +29,11 @@ providers:
       model: Prompt-Guard-86M
   memory:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -41,5 +41,5 @@ providers:
         db_path: ~/.llama/runtime/kvstore.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

distributions/together/run.yaml

@@ -34,7 +34,7 @@ providers:
     config: {}
   agents:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       persistence_store:
         namespace: null
@@ -42,5 +42,5 @@ providers:
         db_path: ~/.llama/runtime/kvstore.db
   telemetry:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config: {}

docs/source/distribution_dev/building_distro.md

@@ -35,14 +35,14 @@ the provider types (implementations) you want to use for these APIs.
 
 Tip: use <TAB> to see options for the providers.
 
-> Enter provider for API inference: meta-reference
+> Enter provider for API inference: inline::meta-reference
 > Enter provider for API safety: inline::llama-guard
-> Enter provider for API agents: meta-reference
+> Enter provider for API agents: inline::meta-reference
 > Enter provider for API memory: inline::faiss
-> Enter provider for API datasetio: meta-reference
+> Enter provider for API datasetio: inline::meta-reference
-> Enter provider for API scoring: meta-reference
+> Enter provider for API scoring: inline::meta-reference
-> Enter provider for API eval: meta-reference
+> Enter provider for API eval: inline::meta-reference
-> Enter provider for API telemetry: meta-reference
+> Enter provider for API telemetry: inline::meta-reference
 
  > (Optional) Enter a short description for your Llama Stack:
 

docs/source/getting_started/distributions/self_hosted_distro/meta-reference-gpu.md

@@ -59,7 +59,7 @@ You may change the `config.model` in `run.yaml` to update the model currently be
 ```
 inference:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       model: Llama3.2-11B-Vision-Instruct
       quantization: null

docs/source/getting_started/index.md

@@ -400,7 +400,7 @@ You may change the `config.model` in `run.yaml` to update the model currently be
 ```
 inference:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::meta-reference
     config:
       model: Llama3.2-11B-Vision-Instruct
       quantization: null

docs/zero_to_hero_guide/06_Safety101.ipynb

@@ -67,7 +67,7 @@
     "providers:\n",
     "  inference:\n",
     "  - provider_id: meta-reference\n",
-    "    provider_type: meta-reference\n",
+    "    provider_type: inline::meta-reference\n",
     "    config:\n",
     "      model: Llama3.1-8B-Instruct\n",
     "      torch_seed: 42\n",
@@ -77,7 +77,7 @@
     "      checkpoint_dir: null\n",
     "  safety:\n",
     "  - provider_id: meta-reference\n",
-    "    provider_type: meta-reference\n",
+    "    provider_type: inline::meta-reference\n",
     "    config:\n",
     "      llama_guard_shield:\n",
     "        model: Llama-Guard-3-1B\n",
@@ -94,7 +94,7 @@
     "```bash\n",
     "inference:\n",
     "  - provider_id: meta-reference\n",
-    "    provider_type: meta-reference\n",
+    "    provider_type: inline::meta-reference\n",
     "    config:\n",
     "      model: Llama3.1-8B-Instruct\n",
     "      torch_seed: null\n",
@@ -103,7 +103,7 @@
     "      create_distributed_process_group: true\n",
     "      checkpoint_dir: null\n",
     "  - provider_id: meta1\n",
-    "    provider_type: meta-reference\n",
+    "    provider_type: inline::meta-reference\n",
     "    config:\n",
     "      model: Llama-Guard-3-1B\n",
     "      torch_seed: null\n",

llama_stack/cli/tests/test_stack_config.py

@@ -25,11 +25,11 @@ def up_to_date_config():
         providers:
           inference:
             - provider_id: provider1
-              provider_type: meta-reference
+              provider_type: inline::meta-reference
               config: {{}}
           safety:
             - provider_id: provider1
-              provider_type: meta-reference
+              provider_type: inline::meta-reference
               config:
                 llama_guard_shield:
                   model: Llama-Guard-3-1B
@@ -39,7 +39,7 @@ def up_to_date_config():
                 enable_prompt_guard: false
           memory:
             - provider_id: provider1
-              provider_type: meta-reference
+              provider_type: inline::meta-reference
               config: {{}}
     """.format(
             version=LLAMA_STACK_RUN_CONFIG_VERSION, built_at=datetime.now().isoformat()
@@ -61,13 +61,13 @@ def old_config():
                 host: localhost
                 port: 11434
               routing_key: Llama3.2-1B-Instruct
-            - provider_type: meta-reference
+            - provider_type: inline::meta-reference
               config:
                 model: Llama3.1-8B-Instruct
               routing_key: Llama3.1-8B-Instruct
           safety:
             - routing_key: ["shield1", "shield2"]
-              provider_type: meta-reference
+              provider_type: inline::meta-reference
               config:
                 llama_guard_shield:
                   model: Llama-Guard-3-1B
@@ -77,7 +77,7 @@ def old_config():
                 enable_prompt_guard: false
           memory:
             - routing_key: vector
-              provider_type: meta-reference
+              provider_type: inline::meta-reference
               config: {{}}
         api_providers:
           telemetry:

llama_stack/providers/registry/agents.py

@@ -14,7 +14,7 @@ def available_providers() -> List[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.agents,
-            provider_type="meta-reference",
+            provider_type="inline::meta-reference",
             pip_packages=[
                 "matplotlib",
                 "pillow",

llama_stack/providers/registry/eval.py

@@ -13,7 +13,7 @@ def available_providers() -> List[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.eval,
-            provider_type="meta-reference",
+            provider_type="inline::meta-reference",
             pip_packages=[],
             module="llama_stack.providers.inline.eval.meta_reference",
             config_class="llama_stack.providers.inline.eval.meta_reference.MetaReferenceEvalConfig",

llama_stack/providers/registry/inference.py

@@ -25,14 +25,14 @@ def available_providers() -> List[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.inference,
-            provider_type="meta-reference",
+            provider_type="inline::meta-reference",
             pip_packages=META_REFERENCE_DEPS,
             module="llama_stack.providers.inline.inference.meta_reference",
             config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
         ),
         InlineProviderSpec(
             api=Api.inference,
-            provider_type="meta-reference-quantized",
+            provider_type="inline::meta-reference-quantized",
             pip_packages=(
                 META_REFERENCE_DEPS
                 + [

llama_stack/providers/registry/memory.py

@@ -34,7 +34,7 @@ def available_providers() -> List[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.memory,
-            provider_type="meta-reference",
+            provider_type="inline::meta-reference",
             pip_packages=EMBEDDING_DEPS + ["faiss-cpu"],
             module="llama_stack.providers.inline.memory.faiss",
             config_class="llama_stack.providers.inline.memory.faiss.FaissImplConfig",

llama_stack/providers/registry/safety.py

@@ -19,7 +19,7 @@ def available_providers() -> List[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.safety,
-            provider_type="meta-reference",
+            provider_type="inline::meta-reference",
             pip_packages=[
                 "transformers",
                 "torch --index-url https://download.pytorch.org/whl/cpu",
@@ -30,7 +30,7 @@ def available_providers() -> List[ProviderSpec]:
                 Api.inference,
             ],
             deprecation_error="""
-Provider `meta-reference` for API `safety` does not work with the latest Llama Stack.
+Provider `inline::meta-reference` for API `safety` does not work with the latest Llama Stack.
 
 - if you are using Llama Guard v3, please use the `inline::llama-guard` provider instead.
 - if you are using Prompt Guard, please use the `inline::prompt-guard` provider instead.

llama_stack/providers/registry/scoring.py

@@ -13,7 +13,7 @@ def available_providers() -> List[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.scoring,
-            provider_type="meta-reference",
+            provider_type="inline::meta-reference",
             pip_packages=[],
             module="llama_stack.providers.inline.scoring.meta_reference",
             config_class="llama_stack.providers.inline.scoring.meta_reference.MetaReferenceScoringConfig",

llama_stack/providers/registry/telemetry.py

@@ -13,7 +13,7 @@ def available_providers() -> List[ProviderSpec]:
     return [
         InlineProviderSpec(
             api=Api.telemetry,
-            provider_type="meta-reference",
+            provider_type="inline::meta-reference",
             pip_packages=[],
             module="llama_stack.providers.inline.meta_reference.telemetry",
             config_class="llama_stack.providers.inline.meta_reference.telemetry.ConsoleConfig",