phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 21:01:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor(llama4): remove duplicate implementation, update imports to llama-models, add comprehensive test for tool calling fix (issue #2584)\n\n- Removes all old llama4 code from llama-stack\n- Updates all relevant imports to use llama-models\n- Adds robust pytest to demonstrate arguments_json fix\n- Updates config/scripts as needed for new structure\n- Resolves merge conflicts with updated main branch\n- Fixes mypy and ruff issues

Browse source
This commit is contained in:
skamenan7 2025-07-10 09:39:33 -04:00
parent 126d6698a7
commit 61dc2a9c58
31 changed files with 1476 additions and 205135 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

@ -9,6 +9,8 @@ import os
import sys
from collections.abc import AsyncGenerator
from llama_models.llama4.chat_format import ChatFormat as Llama4ChatFormat
from llama_models.llama4.tokenizer import Tokenizer as Llama4Tokenizer
from pydantic import BaseModel
from termcolor import cprint
@ -47,8 +49,6 @@ from llama_stack.apis.models import Model, ModelType
from llama_stack.log import get_logger
from llama_stack.models.llama.llama3.chat_format import ChatFormat as Llama3ChatFormat
from llama_stack.models.llama.llama3.tokenizer import Tokenizer as Llama3Tokenizer
from llama_stack.models.llama.llama4.chat_format import ChatFormat as Llama4ChatFormat
from llama_stack.models.llama.llama4.tokenizer import Tokenizer as Llama4Tokenizer
from llama_stack.models.llama.sku_list import resolve_model
from llama_stack.models.llama.sku_types import ModelFamily
from llama_stack.providers.datatypes import ModelsProtocolPrivate