phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-20 06:18:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Tests pass with Ollama now

Browse source
This commit is contained in:
Ashwin Bharambe 2024-12-15 17:31:21 -08:00
parent a9a041a1de
commit e51154964f
27 changed files with 83 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/remote/inference/cerebras/cerebras.py
View file

@ -10,7 +10,6 @@ from cerebras.cloud.sdk import AsyncCerebras
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import Message
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_stack.apis.inference import * # noqa: F403

1
llama_stack/providers/remote/inference/databricks/databricks.py
View file

@ -10,7 +10,6 @@ from llama_models.datatypes import CoreModelId
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import Message
from llama_models.llama3.api.tokenizer import Tokenizer
from openai import OpenAI

1
llama_stack/providers/remote/inference/fireworks/fireworks.py
View file

@ -10,7 +10,6 @@ from fireworks.client import Fireworks
from llama_models.datatypes import CoreModelId
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import Message
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.distribution.request_headers import NeedsRequestProviderData

3
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -11,7 +11,6 @@ import httpx
from llama_models.datatypes import CoreModelId
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import Message
from llama_models.llama3.api.tokenizer import Tokenizer
from ollama import AsyncClient
@ -90,7 +89,7 @@ model_aliases = [
CoreModelId.llama3_2_11b_vision_instruct.value,
),
build_model_alias_with_just_provider_model_id(
"llama3.2-vision",
"llama3.2-vision:latest",
CoreModelId.llama3_2_11b_vision_instruct.value,
),
build_model_alias(

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

@ -83,7 +83,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
async def completion(
self,
model_id: str,
content: InterleavedTextMedia,
content: InterleavedContent,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
@ -267,7 +267,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
async def embeddings(
self,
model_id: str,
contents: List[InterleavedTextMedia],
contents: List[InterleavedContent],
) -> EmbeddingsResponse:
raise NotImplementedError()

1
llama_stack/providers/remote/inference/together/together.py
View file

@ -10,7 +10,6 @@ from llama_models.datatypes import CoreModelId
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import Message
from llama_models.llama3.api.tokenizer import Tokenizer
from together import Together

1
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -8,7 +8,6 @@ import logging
from typing import AsyncGenerator
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import Message
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.sku_list import all_registered_models