feat: Add Groq distribution template (#1173)

# What does this PR do?

Create a distribution template using Groq as inference provider.
Link to issue: https://github.com/meta-llama/llama-stack/issues/958


## Test Plan
Run `python llama_stack/scripts/distro_codegen.py` to generate run.yaml
and build.yaml
Test the newly created template by running
`llama stack build --template <template-name>`
`llama stack run <template-name>`

llama_stack/providers/remote/inference/groq/config.py

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Optional
+from typing import Any, Dict, Optional
 
 from pydantic import BaseModel, Field
 
@@ -18,3 +18,15 @@ class GroqConfig(BaseModel):
         default=None,
         description="The Groq API key",
     )
+
+    url: str = Field(
+        default="https://api.groq.com",
+        description="The URL for the Groq AI server",
+    )
+
+    @classmethod
+    def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
+        return {
+            "url": "https://api.groq.com",
+            "api_key": "${env.GROQ_API_KEY}",
+        }

llama_stack/providers/remote/inference/groq/groq.py

@@ -29,17 +29,10 @@ from llama_stack.apis.inference import (
     ToolConfig,
 )
 from llama_stack.distribution.request_headers import NeedsRequestProviderData
-from llama_stack.models.llama.datatypes import (
-    SamplingParams,
-    ToolDefinition,
-    ToolPromptFormat,
-)
-from llama_stack.models.llama.sku_list import CoreModelId
+from llama_stack.models.llama.datatypes import SamplingParams, ToolDefinition, ToolPromptFormat
 from llama_stack.providers.remote.inference.groq.config import GroqConfig
 from llama_stack.providers.utils.inference.model_registry import (
     ModelRegistryHelper,
-    build_hf_repo_model_entry,
-    build_model_entry,
 )
 
 from .groq_utils import (
@@ -47,33 +40,7 @@ from .groq_utils import (
     convert_chat_completion_response,
     convert_chat_completion_response_stream,
 )
-
-_MODEL_ENTRIES = [
-    build_hf_repo_model_entry(
-        "llama3-8b-8192",
-        CoreModelId.llama3_1_8b_instruct.value,
-    ),
-    build_model_entry(
-        "llama-3.1-8b-instant",
-        CoreModelId.llama3_1_8b_instruct.value,
-    ),
-    build_hf_repo_model_entry(
-        "llama3-70b-8192",
-        CoreModelId.llama3_70b_instruct.value,
-    ),
-    build_hf_repo_model_entry(
-        "llama-3.3-70b-versatile",
-        CoreModelId.llama3_3_70b_instruct.value,
-    ),
-    # Groq only contains a preview version for llama-3.2-3b
-    # Preview models aren't recommended for production use, but we include this one
-    # to pass the test fixture
-    # TODO(aidand): Replace this with a stable model once Groq supports it
-    build_hf_repo_model_entry(
-        "llama-3.2-3b-preview",
-        CoreModelId.llama3_2_3b_instruct.value,
-    ),
-]
+from .models import _MODEL_ENTRIES
 
 
 class GroqInferenceAdapter(Inference, ModelRegistryHelper, NeedsRequestProviderData):

llama_stack/providers/remote/inference/groq/models.py

@@ -0,0 +1,35 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from llama_stack.models.llama.sku_list import CoreModelId
+from llama_stack.providers.utils.inference.model_registry import build_model_entry
+
+_MODEL_ENTRIES = [
+    build_model_entry(
+        "llama3-8b-8192",
+        CoreModelId.llama3_1_8b_instruct.value,
+    ),
+    build_model_entry(
+        "llama-3.1-8b-instant",
+        CoreModelId.llama3_1_8b_instruct.value,
+    ),
+    build_model_entry(
+        "llama3-70b-8192",
+        CoreModelId.llama3_70b_instruct.value,
+    ),
+    build_model_entry(
+        "llama-3.3-70b-versatile",
+        CoreModelId.llama3_3_70b_instruct.value,
+    ),
+    # Groq only contains a preview version for llama-3.2-3b
+    # Preview models aren't recommended for production use, but we include this one
+    # to pass the test fixture
+    # TODO(aidand): Replace this with a stable model once Groq supports it
+    build_model_entry(
+        "llama-3.2-3b-preview",
+        CoreModelId.llama3_2_3b_instruct.value,
+    ),
+]