phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 21:00:01 +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

4
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -6,7 +6,6 @@
import asyncio
import logging
from typing import AsyncGenerator, List, Optional, Union
from llama_models.llama3.api.datatypes import (
@ -37,7 +36,6 @@ from llama_stack.apis.inference import (
ToolCallParseStatus,
ToolChoice,
)
from llama_stack.apis.models import Model, ModelType
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.embedding_mixin import (
@ -262,7 +260,7 @@ class MetaReferenceInferenceImpl(
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:

3
llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py
View file

@ -22,6 +22,7 @@ from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
from llama_stack.providers.utils.inference.embedding_mixin import (
SentenceTransformerEmbeddingMixin,
)
from .config import SentenceTransformersInferenceConfig
log = logging.getLogger(__name__)
@ -67,7 +68,7 @@ class SentenceTransformersInferenceImpl(
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:

6
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -10,10 +10,8 @@ import uuid
from typing import AsyncGenerator, List, Optional
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.sku_list import resolve_model
from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.engine.async_llm_engine import AsyncLLMEngine
from vllm.sampling_params import SamplingParams as VLLMSamplingParams
@ -36,7 +34,6 @@ from llama_stack.apis.inference import (
ToolPromptFormat,
)
from llama_stack.apis.models import Model
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.openai_compat import (
OpenAICompatCompletionChoice,
@ -50,7 +47,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
from .config import VLLMConfig
log = logging.getLogger(__name__)
@ -146,7 +142,7 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
sampling_params: Optional[SamplingParams] = SamplingParams(),
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
tool_prompt_format: Optional[ToolPromptFormat] = None,
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,