Merge branch 'main' into add-nim-completion-api

llama_stack/providers/tests/inference/fixtures.py

@@ -17,6 +17,7 @@ from llama_stack.providers.inline.inference.meta_reference import (
 )
 from llama_stack.providers.remote.inference.bedrock import BedrockConfig
 
+from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
 from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
 from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
 from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
@@ -64,6 +65,21 @@ def inference_meta_reference(inference_model) -> ProviderFixture:
     )
 
 
+@pytest.fixture(scope="session")
+def inference_cerebras() -> ProviderFixture:
+    return ProviderFixture(
+        providers=[
+            Provider(
+                provider_id="cerebras",
+                provider_type="remote::cerebras",
+                config=CerebrasImplConfig(
+                    api_key=get_env_or_fail("CEREBRAS_API_KEY"),
+                ).model_dump(),
+            )
+        ],
+    )
+
+
 @pytest.fixture(scope="session")
 def inference_ollama(inference_model) -> ProviderFixture:
     inference_model = (
@@ -206,6 +222,7 @@ INFERENCE_FIXTURES = [
     "vllm_remote",
     "remote",
     "bedrock",
+    "cerebras",
     "nvidia",
     "tgi",
 ]

llama_stack/providers/tests/inference/test_text_inference.py

@@ -95,6 +95,7 @@ class TestInference:
             "remote::together",
             "remote::fireworks",
             "remote::nvidia",
+            "remote::cerebras",
         ):
             pytest.skip("Other inference providers don't support completion() yet")
 
@@ -139,6 +140,8 @@ class TestInference:
             "remote::together",
             "remote::fireworks",
             "remote::nvidia",
+            "remote::vllm",
+            "remote::cerebras",
         ):
             pytest.skip(
                 "Other inference providers don't support structured output in completions yet"
@@ -198,6 +201,7 @@ class TestInference:
             "remote::fireworks",
             "remote::tgi",
             "remote::together",
+            "remote::vllm",
             "remote::nvidia",
         ):
             pytest.skip("Other inference providers don't support structured output yet")
@@ -211,7 +215,15 @@ class TestInference:
         response = await inference_impl.chat_completion(
             model_id=inference_model,
             messages=[
-                SystemMessage(content="You are a helpful assistant."),
+                # we include context about Michael Jordan in the prompt so that the test is
+                # focused on the funtionality of the model and not on the information embedded
+                # in the model. Llama 3.2 3B Instruct tends to think MJ played for 14 seasons.
+                SystemMessage(
+                    content=(
+                        "You are a helpful assistant.\n\n"
+                        "Michael Jordan was born in 1963. He played basketball for the Chicago Bulls for 15 seasons."
+                    )
+                ),
                 UserMessage(content="Please give me information about Michael Jordan."),
             ],
             stream=False,