phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 02:52:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

infer tool prompt format

Browse source
This commit is contained in:
Dinesh Yeduguru 2025-01-09 17:22:18 -08:00
parent 4938f2fe5d
commit 5f69747b89
21 changed files with 29 additions and 87 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -10,7 +10,6 @@ from typing import AsyncGenerator, List, Optional, Union
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 openai import OpenAI
from llama_stack.apis.common.content_types import InterleavedContent
@ -33,7 +32,6 @@ from llama_stack.apis.inference import (
)
from llama_stack.apis.models import Model, ModelType
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.model_registry import (
build_model_alias,
ModelRegistryHelper,
@ -54,7 +52,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
from .config import VLLMInferenceAdapterConfig
log = logging.getLogger(__name__)
@ -105,7 +102,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
tool_prompt_format: Optional[ToolPromptFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator: