Merge branch 'main' into evals_8

llama_stack/providers/tests/inference/test_inference.py

@@ -138,11 +138,13 @@ async def test_completion(inference_settings):
         "meta-reference",
         "remote::ollama",
         "remote::tgi",
+        "remote::together",
+        "remote::fireworks",
     ):
         pytest.skip("Other inference providers don't support completion() yet")
 
     response = await inference_impl.completion(
-        content="Roses are red,",
+        content="Micheael Jordan is born in ",
         stream=False,
         model=params["model"],
         sampling_params=SamplingParams(
@@ -151,7 +153,7 @@ async def test_completion(inference_settings):
     )
 
     assert isinstance(response, CompletionResponse)
-    assert "violets are blue" in response.content
+    assert "1963" in response.content
 
     chunks = [
         r
@@ -166,7 +168,7 @@ async def test_completion(inference_settings):
     ]
 
     assert all(isinstance(chunk, CompletionResponseStreamChunk) for chunk in chunks)
-    assert len(chunks) == 51
+    assert len(chunks) >= 1
     last = chunks[-1]
     assert last.stop_reason == StopReason.out_of_tokens
 
@@ -180,6 +182,8 @@ async def test_completions_structured_output(inference_settings):
     if provider.__provider_spec__.provider_type not in (
         "meta-reference",
         "remote::tgi",
+        "remote::together",
+        "remote::fireworks",
     ):
         pytest.skip(
             "Other inference providers don't support structured output in completions yet"