phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 19:39:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Tests pass with Ollama now

Browse source
This commit is contained in:
Ashwin Bharambe 2024-12-15 17:31:21 -08:00
parent a9a041a1de
commit e51154964f
27 changed files with 83 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/apis/batch_inference/batch_inference.py
View file

@ -17,7 +17,7 @@ from llama_stack.apis.inference import * # noqa: F403
@json_schema_type
class BatchCompletionRequest(BaseModel):
model: str
content_batch: List[InterleavedTextMedia]
content_batch: List[InterleavedContent]
sampling_params: Optional[SamplingParams] = SamplingParams()
logprobs: Optional[LogProbConfig] = None
@ -53,7 +53,7 @@ class BatchInference(Protocol):
async def batch_completion(
self,
model: str,
content_batch: List[InterleavedTextMedia],
content_batch: List[InterleavedContent],
sampling_params: Optional[SamplingParams] = SamplingParams(),
logprobs: Optional[LogProbConfig] = None,
) -> BatchCompletionResponse: ...