phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 13:52:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

use provider resource id to validate for models

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-12 08:21:37 -08:00
parent e4f14eafe2
commit 95b7f57d92
7 changed files with 75 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

29
llama_stack/providers/tests/inference/fixtures.py
View file

@ -142,6 +142,31 @@ def inference_bedrock() -> ProviderFixture:
)
def get_model_short_name(model_name: str) -> str:
"""Convert model name to a short test identifier.
Args:
model_name: Full model name like "Llama3.1-8B-Instruct"
Returns:
Short name like "llama_8b" suitable for test markers
"""
model_name = model_name.lower()
if "vision" in model_name:
return "llama_vision"
elif "3b" in model_name:
return "llama_3b"
elif "8b" in model_name:
return "llama_8b"
else:
return model_name.replace(".", "_").replace("-", "_")
@pytest.fixture(scope="session")
def model_id(inference_model) -> str:
return get_model_short_name(inference_model)
INFERENCE_FIXTURES = [
"meta_reference",
"ollama",
@ -154,7 +179,7 @@ INFERENCE_FIXTURES = [
@pytest_asyncio.fixture(scope="session")
async def inference_stack(request, inference_model):
async def inference_stack(request, inference_model, model_id):
fixture_name = request.param
inference_fixture = request.getfixturevalue(f"inference_{fixture_name}")
impls = await resolve_impls_for_test_v2(
@ -163,7 +188,7 @@ async def inference_stack(request, inference_model):
inference_fixture.provider_data,
models=[
ModelInput(
model_id=inference_model,
model_id=model_id,
)
],
)

41
llama_stack/providers/tests/inference/test_text_inference.py
View file

@ -64,7 +64,7 @@ def sample_tool_definition():
class TestInference:
@pytest.mark.asyncio
async def test_model_list(self, inference_model, inference_stack):
async def test_model_list(self, inference_model, inference_stack, model_id):
_, models_impl = inference_stack
response = await models_impl.list_models()
assert isinstance(response, list)
@ -73,17 +73,16 @@ class TestInference:
model_def = None
for model in response:
if model.identifier == inference_model:
if model.identifier == model_id:
model_def = model
break
assert model_def is not None
@pytest.mark.asyncio
async def test_completion(self, inference_model, inference_stack):
async def test_completion(self, inference_model, inference_stack, model_id):
inference_impl, _ = inference_stack
provider = inference_impl.routing_table.get_provider_impl(inference_model)
provider = inference_impl.routing_table.get_provider_impl(model_id)
if provider.__provider_spec__.provider_type not in (
"meta-reference",
"remote::ollama",
@ -96,7 +95,7 @@ class TestInference:
response = await inference_impl.completion(
content="Micheael Jordan is born in ",
stream=False,
model=inference_model,
model_id=model_id,
sampling_params=SamplingParams(
max_tokens=50,
),
@ -110,7 +109,7 @@ class TestInference:
async for r in await inference_impl.completion(
content="Roses are red,",
stream=True,
model=inference_model,
model_id=model_id,
sampling_params=SamplingParams(
max_tokens=50,
),
@ -125,11 +124,11 @@ class TestInference:
@pytest.mark.asyncio
@pytest.mark.skip("This test is not quite robust")
async def test_completions_structured_output(
self, inference_model, inference_stack
self, inference_model, inference_stack, model_id
):
inference_impl, _ = inference_stack
provider = inference_impl.routing_table.get_provider_impl(inference_model)
provider = inference_impl.routing_table.get_provider_impl(model_id)
if provider.__provider_spec__.provider_type not in (
"meta-reference",
"remote::tgi",
@ -149,7 +148,7 @@ class TestInference:
response = await inference_impl.completion(
content=user_input,
stream=False,
model=inference_model,
model_id=model_id,
sampling_params=SamplingParams(
max_tokens=50,
),
@ -167,11 +166,11 @@ class TestInference:
@pytest.mark.asyncio
async def test_chat_completion_non_streaming(
self, inference_model, inference_stack, common_params, sample_messages
self, inference_model, inference_stack, common_params, sample_messages, model_id
):
inference_impl, _ = inference_stack
response = await inference_impl.chat_completion(
model=inference_model,
model_id=model_id,
messages=sample_messages,
stream=False,
**common_params,
@ -184,11 +183,11 @@ class TestInference:
@pytest.mark.asyncio
async def test_structured_output(
self, inference_model, inference_stack, common_params
self, inference_model, inference_stack, common_params, model_id
):
inference_impl, _ = inference_stack
provider = inference_impl.routing_table.get_provider_impl(inference_model)
provider = inference_impl.routing_table.get_provider_impl(model_id)
if provider.__provider_spec__.provider_type not in (
"meta-reference",
"remote::fireworks",
@ -204,7 +203,7 @@ class TestInference:
num_seasons_in_nba: int
response = await inference_impl.chat_completion(
model=inference_model,
model_id=model_id,
messages=[
SystemMessage(content="You are a helpful assistant."),
UserMessage(content="Please give me information about Michael Jordan."),
@ -227,7 +226,7 @@ class TestInference:
assert answer.num_seasons_in_nba == 15
response = await inference_impl.chat_completion(
model=inference_model,
model_id=model_id,
messages=[
SystemMessage(content="You are a helpful assistant."),
UserMessage(content="Please give me information about Michael Jordan."),
@ -244,13 +243,13 @@ class TestInference:
@pytest.mark.asyncio
async def test_chat_completion_streaming(
self, inference_model, inference_stack, common_params, sample_messages
self, inference_model, inference_stack, common_params, sample_messages, model_id
):
inference_impl, _ = inference_stack
response = [
r
async for r in await inference_impl.chat_completion(
model=inference_model,
model_id=model_id,
messages=sample_messages,
stream=True,
**common_params,
@ -277,6 +276,7 @@ class TestInference:
common_params,
sample_messages,
sample_tool_definition,
model_id,
):
inference_impl, _ = inference_stack
messages = sample_messages + [
@ -286,7 +286,7 @@ class TestInference:
]
response = await inference_impl.chat_completion(
model=inference_model,
model_id=model_id,
messages=messages,
tools=[sample_tool_definition],
stream=False,
@ -316,6 +316,7 @@ class TestInference:
common_params,
sample_messages,
sample_tool_definition,
model_id,
):
inference_impl, _ = inference_stack
messages = sample_messages + [
@ -327,7 +328,7 @@ class TestInference:
response = [
r
async for r in await inference_impl.chat_completion(
model=inference_model,
model_id=model_id,
messages=messages,
tools=[sample_tool_definition],
stream=True,