phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-07 09:49:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix params

Browse source
This commit is contained in:
Xi Yan 2025-03-07 12:39:44 -08:00
parent d86a893ead
commit da373471e4
1 changed files with 4 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/remote/inference/together/together.py
View file

@ -32,9 +32,7 @@ from llama_stack.apis.inference import (
) )
from llama_stack.distribution.request_headers import NeedsRequestProviderData from llama_stack.distribution.request_headers import NeedsRequestProviderData
from llama_stack.log import get_logger from llama_stack.log import get_logger
from llama_stack.providers.utils.inference.model_registry import ( from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.openai_compat import ( from llama_stack.providers.utils.inference.openai_compat import (
convert_message_to_openai_dict, convert_message_to_openai_dict,
get_sampling_options, get_sampling_options,
@ -179,8 +177,10 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
) )
if stream: if stream:
print("STREAMING", request)
return self._stream_chat_completion(request) return self._stream_chat_completion(request)
else: else:
print("NON STREAMING", request)
return await self._nonstream_chat_completion(request) return await self._nonstream_chat_completion(request)
async def _nonstream_chat_completion(self, request: ChatCompletionRequest) -> ChatCompletionResponse: 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), **self._build_options(request.sampling_params, request.logprobs, request.response_format),
} }
logger.debug(f"params to together: {params}") logger.debug(f"params to together: {params}")
return params
async def embeddings( async def embeddings(
self, self,