phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 23:00:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix after rebasing, now test isn't working

Browse source
This commit is contained in:
Honglin Cao 2025-02-04 16:59:56 -05:00
parent 102af46d5d
commit acc4d75c48
3 changed files with 17 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/centml/centml.py
View file

@ -17,6 +17,7 @@ from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
CompletionResponse,
EmbeddingsResponse,
Inference,
LogProbConfig,
@ -25,6 +26,7 @@ from llama_stack.apis.inference import (
ResponseFormatType,
SamplingParams,
ToolChoice,
ToolConfig,
ToolDefinition,
ToolPromptFormat,
)
@ -42,6 +44,7 @@ from llama_stack.providers.utils.inference.openai_compat import (
process_completion_stream_response,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
completion_request_to_prompt,
content_has_media,
interleaved_content_as_str,
@ -176,6 +179,7 @@ class CentMLInferenceAdapter(
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
tool_config: Optional[ToolConfig] = None,
) -> AsyncGenerator:
"""
For "chat completion" style requests.