phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-11 11:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-18 20:46:48 -07:00
parent 072d1b7205
commit fedc11b726
2 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/impls/meta_reference/inference/inference.py
View file

@ -95,7 +95,7 @@ class MetaReferenceInferenceImpl(Inference, ModelsProtocolPrivate):
def impl(): def impl():
stop_reason = None stop_reason = None
for token_result in self.generator.chat_completion(request): for token_result in self.generator.completion(request):
if token_result.text == "<|eot_id|>": if token_result.text == "<|eot_id|>":
stop_reason = StopReason.end_of_turn stop_reason = StopReason.end_of_turn
text = "" text = ""

5
llama_stack/providers/tests/inference/test_inference.py
View file

@ -159,7 +159,10 @@ async def test_completion(inference_settings):
) )
] ]
print(chunks) assert all(isinstance(chunk, CompletionResponseStreamChunk) for chunk in chunks)
assert len(chunks) == 51
last = chunks[-1]
assert last.stop_reason == StopReason.out_of_tokens
@pytest.mark.asyncio @pytest.mark.asyncio