phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-16 09:58:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into chore/standard-unsupported-model-err-msg-2517

Browse source
This commit is contained in:
Rohan Awhad 2025-06-26 10:53:28 -04:00
commit 92d934e476
196 changed files with 2335 additions and 1516 deletions
Download patch file Download diff file Expand all files Collapse all files

18
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -23,6 +23,13 @@ from llama_stack.apis.inference import (
JsonSchemaResponseFormat,
LogProbConfig,
Message,
OpenAIChatCompletion,
OpenAIChatCompletionChunk,
OpenAICompletion,
OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage,
OpenAIMessageParam,
OpenAIResponseFormatParam,
ResponseFormat,
SamplingParams,
TextTruncation,
@ -31,16 +38,7 @@ from llama_stack.apis.inference import (
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.inference.inference import (
OpenAIChatCompletion,
OpenAIChatCompletionChunk,
OpenAICompletion,
OpenAIEmbeddingsResponse,
OpenAIEmbeddingUsage,
OpenAIMessageParam,
OpenAIResponseFormatParam,
)
from llama_stack.apis.models.models import Model
from llama_stack.apis.models import Model
from llama_stack.distribution.request_headers import NeedsRequestProviderData
from llama_stack.exceptions import UnsupportedModelError
from llama_stack.log import get_logger

6
llama_stack/providers/utils/inference/model_registry.py
View file

@ -8,7 +8,7 @@ from typing import Any
from pydantic import BaseModel, Field
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.models import ModelType
from llama_stack.exceptions import UnsupportedModelError
from llama_stack.models.llama.sku_list import all_registered_models
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
@ -35,7 +35,9 @@ def get_huggingface_repo(model_descriptor: str) -> str | None:
def build_hf_repo_model_entry(
provider_model_id: str, model_descriptor: str, additional_aliases: list[str] | None = None
provider_model_id: str,
model_descriptor: str,
additional_aliases: list[str] | None = None,
) -> ProviderModelEntry:
aliases = [
get_huggingface_repo(model_descriptor),

26
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -95,27 +95,25 @@ from llama_stack.apis.inference import (
CompletionResponse,
CompletionResponseStreamChunk,
GreedySamplingStrategy,
Message,
SamplingParams,
SystemMessage,
TokenLogProbs,
ToolChoice,
ToolResponseMessage,
TopKSamplingStrategy,
TopPSamplingStrategy,
UserMessage,
)
from llama_stack.apis.inference.inference import (
JsonSchemaResponseFormat,
Message,
OpenAIChatCompletion,
OpenAICompletion,
OpenAICompletionChoice,
OpenAIEmbeddingData,
OpenAIMessageParam,
OpenAIResponseFormatParam,
SamplingParams,
SystemMessage,
TokenLogProbs,
ToolChoice,
ToolConfig,
ToolResponseMessage,
TopKSamplingStrategy,
TopPSamplingStrategy,
UserMessage,
)
from llama_stack.apis.inference.inference import (
from llama_stack.apis.inference import (
OpenAIChoice as OpenAIChatCompletionChoice,
)
from llama_stack.models.llama.datatypes import (
@ -1026,7 +1024,9 @@ def openai_messages_to_messages(
return converted_messages
def openai_content_to_content(content: str | Iterable[OpenAIChatCompletionContentPartParam]):
def openai_content_to_content(content: str | Iterable[OpenAIChatCompletionContentPartParam] | None):
if content is None:
return ""
if isinstance(content, str):
return content
elif isinstance(content, list):