From da373471e42caf1fdb569b948b5366044f441c67 Mon Sep 17 00:00:00 2001 From: Xi Yan Date: Fri, 7 Mar 2025 12:39:44 -0800 Subject: [PATCH] fix params --- .../providers/remote/inference/together/together.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/llama_stack/providers/remote/inference/together/together.py b/llama_stack/providers/remote/inference/together/together.py index f701c0da7..1100d1618 100644 --- a/llama_stack/providers/remote/inference/together/together.py +++ b/llama_stack/providers/remote/inference/together/together.py @@ -32,9 +32,7 @@ from llama_stack.apis.inference import ( ) from llama_stack.distribution.request_headers import NeedsRequestProviderData from llama_stack.log import get_logger -from llama_stack.providers.utils.inference.model_registry import ( - ModelRegistryHelper, -) +from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper from llama_stack.providers.utils.inference.openai_compat import ( convert_message_to_openai_dict, get_sampling_options, @@ -179,8 +177,10 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi ) if stream: + print("STREAMING", request) return self._stream_chat_completion(request) else: + print("NON STREAMING", request) return await self._nonstream_chat_completion(request) async def _nonstream_chat_completion(self, request: ChatCompletionRequest) -> ChatCompletionResponse: @@ -227,6 +227,7 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi **self._build_options(request.sampling_params, request.logprobs, request.response_format), } logger.debug(f"params to together: {params}") + return params async def embeddings( self,