phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 20:59:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

several fixes

Browse source
This commit is contained in:
Ashwin Bharambe 2025-04-07 10:31:20 -07:00
parent e2e2820c9a
commit 53a8086e37
60 changed files with 1006 additions and 1078 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/utils/inference/__init__.py
View file

@ -6,8 +6,8 @@
from typing import List
from llama_stack.models.llama.datatypes import * # noqa: F403
from llama_stack.models.llama.sku_list import all_registered_models
from llama_stack.models.llama.sku_types import * # noqa: F403
def is_supported_safety_model(model: Model) -> bool:

8
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -73,21 +73,21 @@ from llama_stack.apis.inference import (
CompletionMessage,
CompletionResponse,
CompletionResponseStreamChunk,
GreedySamplingStrategy,
Message,
SamplingParams,
SystemMessage,
TokenLogProbs,
ToolResponseMessage,
TopKSamplingStrategy,
TopPSamplingStrategy,
UserMessage,
)
from llama_stack.models.llama.datatypes import (
BuiltinTool,
GreedySamplingStrategy,
SamplingParams,
StopReason,
ToolCall,
ToolDefinition,
TopKSamplingStrategy,
TopPSamplingStrategy,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
convert_image_content_to_url,

3
llama_stack/providers/utils/inference/prompt_adapter.py
View file

@ -34,7 +34,6 @@ from llama_stack.apis.inference import (
)
from llama_stack.log import get_logger
from llama_stack.models.llama.datatypes import (
ModelFamily,
RawContent,
RawContentItem,
RawMediaItem,
@ -43,7 +42,6 @@ from llama_stack.models.llama.datatypes import (
Role,
StopReason,
ToolPromptFormat,
is_multimodal,
)
from llama_stack.models.llama.llama3.chat_format import ChatFormat
from llama_stack.models.llama.llama3.prompt_templates import (
@ -55,6 +53,7 @@ from llama_stack.models.llama.llama3.prompt_templates import (
)
from llama_stack.models.llama.llama3.tokenizer import Tokenizer
from llama_stack.models.llama.sku_list import resolve_model
from llama_stack.models.llama.sku_types import ModelFamily, is_multimodal
from llama_stack.providers.utils.inference import supported_inference_models
log = get_logger(name=__name__, category="inference")