phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 23:02:16 +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

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

@ -8,7 +8,6 @@ from typing import AsyncGenerator, List, Optional, Union
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.tokenizer import Tokenizer
@ -52,7 +51,6 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
from .config import FireworksImplConfig
MODEL_ALIASES = [
build_model_alias(
"fireworks/llama-v3p1-8b-instruct",
@ -198,7 +196,7 @@ class FireworksInferenceAdapter(
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,