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
"""A transformers class whose _supports_sdpa resolves False (Mamba, FalconMamba) resolves to eager even when
the zoo's source probe reports sdpa: transformers raises "does not support ... scaled_dot_product_attention"."""
from types import SimpleNamespace
import pytest
import unsloth # noqa: F401
from unsloth.models import _utils
@pytest.fixture(autouse = True)
def _no_flash(monkeypatch):
monkeypatch.setattr(_utils, "HAS_FLASH_ATTENTION", False, raising = False)
@pytest.mark.parametrize(
"module_name, class_name, model_type",
[
("transformers.models.mamba.modeling_mamba", "MambaForCausalLM", "mamba"),
(
"transformers.models.falcon_mamba.modeling_falcon_mamba",
"FalconMambaForCausalLM",
"falcon_mamba",
),
],
)
def test_real_mamba_classes_resolve_to_eager(module_name, class_name, model_type):
cls = getattr(pytest.importorskip(module_name), class_name)
if cls._supports_sdpa:
pytest.skip(reason = f"this transformers gives {class_name} an sdpa path")
config = SimpleNamespace(model_type = model_type)
# supports_sdpa = True is what unsloth_compile_transformers reports for these classes.
impl = _utils.resolve_attention_implementation(cls, config, supports_sdpa = True)
assert impl == "eager"
# The resolved value is what the loader stamps on the config and passes to from_pretrained.
assert config._attn_implementation == "eager"
def test_native_class_with_sdpa_keeps_sdpa():
from transformers.models.llama.modeling_llama import LlamaForCausalLM
assert LlamaForCausalLM._supports_sdpa
config = SimpleNamespace(model_type = "llama", attention_dropout = 0)
assert (
_utils.resolve_attention_implementation(LlamaForCausalLM, config, supports_sdpa = True)
== "sdpa"
)
def test_only_transformers_classes_are_checked():
# Remote code that does not declare _supports_sdpa keeps the source-probe answer.
remote = type("RemoteForCausalLM", (), {"__module__": "transformers_modules.repo.modeling"})
remote._supports_sdpa = False
assert not _utils._native_class_refuses_sdpa(remote)
native = type("NativeForCausalLM", (), {"__module__": "transformers.models.x.modeling_x"})
native._supports_sdpa = False
assert _utils._native_class_refuses_sdpa(native)
native._supports_sdpa = True
assert not _utils._native_class_refuses_sdpa(native)
assert not _utils._native_class_refuses_sdpa(None)