phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-19 08:59:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

ollama import remove

Browse source
This commit is contained in:
Xi Yan 2024-12-26 18:07:18 -08:00
parent 165777a181
commit f97638a323
3 changed files with 43 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

21
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -13,10 +13,25 @@ from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.sku_list import all_registered_models
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.apis.models import * # noqa: F403
from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
EmbeddingsResponse,
Inference,
LogProbConfig,
Message,
ResponseFormat,
ResponseFormatType,
SamplingParams,
ToolChoice,
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.models import Model
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.model_registry import (
build_model_alias,
ModelRegistryHelper,