phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 19:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

rename augment_messages

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-08 13:48:44 -07:00 • committed by Ashwin Bharambe
parent 336cf7a674
commit 640c5c54f7
10 changed files with 34 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/impls/meta_reference/inference/inference.py
View file

@ -12,8 +12,8 @@ from llama_models.sku_list import resolve_model
from llama_models.llama3.api.datatypes import * # noqa: F403
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.augment_messages import (
augment_messages_for_tools,
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_messages,
)
from .config import MetaReferenceImplConfig
@ -94,7 +94,7 @@ class MetaReferenceInferenceImpl(Inference):
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest
) -> ChatCompletionResponse:
messages = augment_messages_for_tools(request)
messages = chat_completion_request_to_messages(request)
tokens = []
logprobs = []
@ -136,7 +136,7 @@ class MetaReferenceInferenceImpl(Inference):
async def _stream_chat_completion(
self, request: ChatCompletionRequest
) -> AsyncGenerator:
messages = augment_messages_for_tools(request)
messages = chat_completion_request_to_messages(request)
yield ChatCompletionResponseStreamChunk(
event=ChatCompletionResponseEvent(

7
llama_stack/providers/impls/vllm/vllm.py
View file

@ -19,10 +19,6 @@ from vllm.sampling_params import SamplingParams
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.augment_messages import (
chat_completion_request_to_prompt,
)
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from llama_stack.providers.utils.inference.openai_compat import (
OpenAICompatCompletionChoice,
@ -30,6 +26,9 @@ from llama_stack.providers.utils.inference.openai_compat import (
process_chat_completion_response,
process_chat_completion_stream_response,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
)
from .config import VLLMConfig