phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-15 04:22:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Removed additional dead code

Browse source
This commit is contained in:
Omar Abdelwahab 2025-10-06 11:39:14 -07:00
parent f6080040da
commit 8809a34b23
2 changed files with 166 additions and 169 deletions
Download patch file Download diff file Expand all files Collapse all files

28
llama_stack/apis/inference/inference.py
View file

@ -351,34 +351,6 @@ class CompletionRequest(BaseModel):
logprobs: LogProbConfig | None = None
# @json_schema_type
# class CompletionResponse(MetricResponseMixin):
# """Response from a completion request.
# :param content: The generated completion text
# :param stop_reason: Reason why generation stopped
# :param logprobs: Optional log probabilities for generated tokens
# """
# content: str
# stop_reason: StopReason
# logprobs: list[TokenLogProbs] | None = None
# @json_schema_type
# class CompletionResponseStreamChunk(MetricResponseMixin):
# """A chunk of a streamed completion response.
# :param delta: New content generated since last chunk. This can be one or more tokens.
# :param stop_reason: Optional reason why generation stopped, if complete
# :param logprobs: Optional log probabilities for generated tokens
# """
# delta: str
# stop_reason: StopReason | None = None
# logprobs: list[TokenLogProbs] | None = None
class SystemMessageBehavior(Enum):
"""Config for how to override the default system prompt.