phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

migrate apis without implementations

Browse source
This commit is contained in:
Xi Yan 2024-09-11 14:15:13 -07:00
parent 6049aada71
commit a3081f28fc
7 changed files with 90 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_toolchain/batch_inference/api/api.py
View file

@ -51,11 +51,21 @@ class BatchInference(Protocol):
@webmethod(route="/batch_inference/completion")
async def batch_completion(
self,
request: BatchCompletionRequest,
model: str,
content_batch: List[InterleavedTextMedia],
sampling_params: Optional[SamplingParams] = SamplingParams(),
logprobs: Optional[LogProbConfig] = None,
) -> BatchCompletionResponse: ...
@webmethod(route="/batch_inference/chat_completion")
async def batch_chat_completion(
self,
request: BatchChatCompletionRequest,
model: str,
messages_batch: List[List[Message]],
sampling_params: Optional[SamplingParams] = SamplingParams(),
# zero-shot tool definitions as input to the model
tools: Optional[List[ToolDefinition]] = list,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
logprobs: Optional[LogProbConfig] = None,
) -> BatchChatCompletionResponse: ...