Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
"""Off/fit/always multi-model mode in owner's DB; legacy keep_multiple_models_loaded can force off."""
from __future__ import annotations
import threading
import time
from typing import Any
from utils.account_context import OWNER, run_as
MULTI_MODEL_SETTING_KEY = "keep_multiple_models_loaded"
MULTI_MODEL_MODE_SETTING_KEY = "multi_model_mode"
MULTI_MODEL_MODE_CHOICES = ("off", "fit", "always")
_VALID_MODES = frozenset(MULTI_MODEL_MODE_CHOICES)
DEFAULT_MULTI_MODEL_MODE = "off"
DEFAULT_MULTI_MODEL_ENABLED = False
# Read on every load, including media loads, so memo briefly to spare SQLite.
_CACHE_TTL_S = 2.0
_cache_lock = threading.Lock()
_cache: tuple[float, str] | None = None
# Bumped on every write, so a read that began before a write never caches the old value.
_generation = 0
_MAX_REREADS = 3
def _mode_from_stored(stored: dict[str, Any]) -> str:
if stored.get(MULTI_MODEL_SETTING_KEY) is not True:
return "off"
return "always" if stored.get(MULTI_MODEL_MODE_SETTING_KEY) == "always" else "fit"
def _read_mode() -> str:
from storage.studio_db import get_app_settings
stored = run_as(
OWNER,
get_app_settings,
[MULTI_MODEL_SETTING_KEY, MULTI_MODEL_MODE_SETTING_KEY],
)
return _mode_from_stored(stored)
def get_multi_model_mode() -> str:
"""``"off"``, ``"fit"`` or ``"always"``, read as the owner."""
global _cache
mode = DEFAULT_MULTI_MODEL_MODE
for _attempt in range(_MAX_REREADS):
with _cache_lock:
if _cache is not None and time.monotonic() - _cache[0] < _CACHE_TTL_S:
return _cache[1]
generation = _generation
try:
mode = _read_mode()
except Exception:
# An unreadable DB must not fail a load: keep the last mode read, else the default.
with _cache_lock:
return _cache[1] if _cache is not None else DEFAULT_MULTI_MODEL_MODE
with _cache_lock:
if _generation == generation:
_cache = (time.monotonic(), mode)
return mode
return mode
def get_multi_model_enabled() -> bool:
return get_multi_model_mode() != "off"
def invalidate_multi_model_cache() -> None:
global _cache, _generation
with _cache_lock:
_cache = None
_generation += 1
def set_multi_model_mode(value: Any) -> bool:
"""Store the mode and return whether it changed."""
if not isinstance(value, str) or value not in _VALID_MODES:
raise ValueError("Keep multiple models loaded must be off, fit or always.")
from storage.studio_db import upsert_app_settings
previous = _read_mode()
run_as(
OWNER,
upsert_app_settings,
{MULTI_MODEL_MODE_SETTING_KEY: value, MULTI_MODEL_SETTING_KEY: value != "off"},
)
invalidate_multi_model_cache()
return previous != value
def set_multi_model_enabled(value: Any) -> bool:
"""Legacy bool write: True keeps an existing When they fit or Always, False turns it off."""
if not isinstance(value, bool):
raise ValueError("Keep multiple models loaded must be true or false.")
if not value:
set_multi_model_mode("off")
elif _read_mode() == "off":
set_multi_model_mode("fit")
return value