ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

[pre-commit.ci] auto fixes from pre-commit.com hooks

Browse source 
for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2026-07-01 04:01:36 +00:00
commit 80feeb1f0c
3 changed files with 57 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

4
studio/backend/core/inference/diffusion.py
View file

@ -1188,9 +1188,7 @@ class DiffusionBackend:
"native engine for GGUF models."
)
resolved = diffusion_lora.resolve_specs(
specs, hf_token = state.hf_token, cancel_event = cancel
)
resolved = diffusion_lora.resolve_specs(specs, hf_token = state.hf_token, cancel_event = cancel)
# Unique adapter names (diffusers requires distinct names; sanitized stems can collide).
uniq: list[tuple[str, str, float]] = []
seen: set[str] = set()

16
studio/backend/core/inference/diffusion_lora.py
View file

@ -243,7 +243,9 @@ def materialize_native_dir(resolved: list[ResolvedLora], dest: Path) -> list[Res
n += 1
alias = f"{r.alias}_{n}"
used.add(alias)
ext = os.path.splitext(r.path)[1].lower() or (".gguf" if r.fmt == "gguf" else ".safetensors")
ext = os.path.splitext(r.path)[1].lower() or (
".gguf" if r.fmt == "gguf" else ".safetensors"
)
link = dest / f"{alias}{ext}"
try:
if link.exists() or link.is_symlink():
@ -251,7 +253,6 @@ def materialize_native_dir(resolved: list[ResolvedLora], dest: Path) -> list[Res
os.symlink(os.path.realpath(r.path), link)
except OSError:
import shutil
shutil.copy2(r.path, link)
out.append(ResolvedLora(r.id, alias, str(link), r.fmt, r.weight))
return out
@ -286,7 +287,16 @@ def _fmt_weight(w: float) -> str:
# Families the native sd-cli LoRA name-conversion supports (SD1.5/SD2/SDXL/SD3/FLUX/
# z-image). Qwen-Image has no LoRA branch in stable-diffusion.cpp -> excluded until
# validated. Matched by substring against the resolved family name.
_NATIVE_LORA_FAMILY_TOKENS = ("flux.1", "flux.2", "z-image", "sd1", "sd2", "sdxl", "sd3", "stable-diffusion")
_NATIVE_LORA_FAMILY_TOKENS = (
"flux.1",
"flux.2",
"z-image",
"sd1",
"sd2",
"sdxl",
"sd3",
"stable-diffusion",
)
# Diffusers quant schemes that cannot take LoRA cleanly (torchao tensor-subclass weights).
_DIFFUSERS_LORA_BLOCKED_QUANT = ("int8", "fp8", "nvfp4", "mxfp8")

57
studio/backend/tests/test_diffusion_lora.py
View file

@ -42,15 +42,31 @@ def test_inject_prompt_tags_empty_returns_prompt():
def test_supports_lora_matrix():
# native: flux/z-image yes, qwen no
assert dl.supports_lora(engine = "sd_cpp", family = "flux.1", model_kind = "gguf", transformer_quant = None)
assert dl.supports_lora(engine = "sd_cpp", family = "z-image", model_kind = "gguf", transformer_quant = None)
assert not dl.supports_lora(engine = "sd_cpp", family = "qwen-image", model_kind = "gguf", transformer_quant = None)
assert dl.supports_lora(
engine = "sd_cpp", family = "flux.1", model_kind = "gguf", transformer_quant = None
)
assert dl.supports_lora(
engine = "sd_cpp", family = "z-image", model_kind = "gguf", transformer_quant = None
)
assert not dl.supports_lora(
engine = "sd_cpp", family = "qwen-image", model_kind = "gguf", transformer_quant = None
)
# diffusers: bf16 yes, fp8/int8 dense no, gguf-diffusers no
assert dl.supports_lora(engine = "diffusers", family = "flux.1", model_kind = "pipeline", transformer_quant = None)
assert dl.supports_lora(engine = "diffusers", family = "flux.1", model_kind = "single_file", transformer_quant = None)
assert not dl.supports_lora(engine = "diffusers", family = "flux.1", model_kind = "single_file", transformer_quant = "fp8")
assert not dl.supports_lora(engine = "diffusers", family = "flux.1", model_kind = "single_file", transformer_quant = "int8")
assert not dl.supports_lora(engine = "diffusers", family = "flux.1", model_kind = "gguf", transformer_quant = None)
assert dl.supports_lora(
engine = "diffusers", family = "flux.1", model_kind = "pipeline", transformer_quant = None
)
assert dl.supports_lora(
engine = "diffusers", family = "flux.1", model_kind = "single_file", transformer_quant = None
)
assert not dl.supports_lora(
engine = "diffusers", family = "flux.1", model_kind = "single_file", transformer_quant = "fp8"
)
assert not dl.supports_lora(
engine = "diffusers", family = "flux.1", model_kind = "single_file", transformer_quant = "int8"
)
assert not dl.supports_lora(
engine = "diffusers", family = "flux.1", model_kind = "gguf", transformer_quant = None
)
def test_materialize_native_dir_symlinks_and_breaks_collisions(tmp_path):
@ -136,10 +152,18 @@ class _FakePipe:
self.active = None
self.unloaded = 0
def load_lora_weights(self, path, adapter_name = None):
def load_lora_weights(
self,
path,
adapter_name = None,
):
self.loaded.append((path, adapter_name))
def set_adapters(self, names, adapter_weights = None):
def set_adapters(
self,
names,
adapter_weights = None,
):
self.active = (list(names), list(adapter_weights) if adapter_weights else None)
def unload_lora_weights(self):
@ -148,7 +172,12 @@ class _FakePipe:
self.active = None
def _fake_state(pipe, *, kind = "pipeline", quant = None):
def _fake_state(
pipe,
*,
kind = "pipeline",
quant = None,
):
fam = types.SimpleNamespace(name = "flux.1")
return types.SimpleNamespace(
pipe = pipe, family = fam, kind = kind, transformer_quant = quant, hf_token = None
@ -157,7 +186,6 @@ def _fake_state(pipe, *, kind = "pipeline", quant = None):
def _backend():
from core.inference.diffusion import DiffusionBackend
return DiffusionBackend()
@ -173,7 +201,9 @@ def test_diffusers_apply_loads_and_sets_adapters(monkeypatch):
],
)
pipe = _FakePipe()
_backend()._apply_loras(_fake_state(pipe), [("styleA", 0.8), ("styleB", 1.0)], threading.Event())
_backend()._apply_loras(
_fake_state(pipe), [("styleA", 0.8), ("styleB", 1.0)], threading.Event()
)
assert [n for _p, n in pipe.loaded] == ["styleA", "styleB"]
assert pipe.active == (["styleA", "styleB"], [0.8, 1.0])
assert getattr(pipe, "_unsloth_loras") # marker recorded
@ -220,7 +250,6 @@ def test_diffusers_apply_clears_when_empty(monkeypatch):
def test_diffusers_apply_rejects_unsupported_quant():
import threading
pipe = _FakePipe()
with pytest.raises(ValueError, match = "not supported"):
_backend()._apply_loras(