phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-19 07:19:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

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

Browse source
This commit is contained in:
Matthew Farrellee 2024-12-11 13:07:23 -05:00
commit df3c239573
199 changed files with 7739 additions and 814 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/providers/tests/inference/test_text_inference.py
View file

@ -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,