phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 17:22:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into aidand-391-guided-decoding-vllm_3

Browse source
This commit is contained in:
Aidan Do 2024-12-08 17:36:57 +11:00 • committed by GitHub
commit 44bb23ebc8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
177 changed files with 5725 additions and 594 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/providers/tests/inference/test_text_inference.py
View file

@ -94,6 +94,7 @@ class TestInference:
"remote::tgi",
"remote::together",
"remote::fireworks",
"remote::cerebras",
):
pytest.skip("Other inference providers don't support completion() yet")
@ -140,6 +141,8 @@ class TestInference:
"remote::together",
"remote::fireworks",
"remote::vllm",
"remote::cerebras",
):
pytest.skip(
"Other inference providers don't support structured output in completions yet"
@ -213,7 +216,15 @@ 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,