Skip to content

[cli] report all quant backends in diffusers-cli env. #13728

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
sayakpaul wants to merge 3 commits into
base: main
Choose a base branch
from
+24 −6
Open

[cli] report all quant backends in diffusers-cli env. #13728

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
648f502
report all quant backends in diffusers-cli env.
sayakpaul May 12, 2026
f82a131
Merge branch 'main' into report-quant-backends-cli
sayakpaul May 13, 2026
07f8087
reduce reporting noise
sayakpaul May 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 24 additions & 6 deletions src/diffusers/commands/env.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.

import importlib.metadata
import platform
import subprocess
from argparse import ArgumentParser
Expand All @@ -23,16 +24,30 @@
is_accelerate_available,
is_bitsandbytes_available,
is_flax_available,
is_gguf_available,
is_google_colab,
is_nvidia_modelopt_available,
is_optimum_quanto_available,
is_peft_available,
is_safetensors_available,
is_torch_available,
is_torchao_available,
is_transformers_available,
is_xformers_available,
)
from . import BaseDiffusersCLICommand


# (display name, availability_fn, pypi distribution name for importlib.metadata.version)
_QUANTIZATION_BACKENDS = (
("bitsandbytes", is_bitsandbytes_available, "bitsandbytes"),
("gguf", is_gguf_available, "gguf"),
("optimum-quanto", is_optimum_quanto_available, "optimum-quanto"),
("torchao", is_torchao_available, "torchao"),
("nvidia-modelopt", is_nvidia_modelopt_available, "nvidia-modelopt"),
)


def info_command_factory(_):
return EnvironmentCommand()

Expand Down Expand Up @@ -92,11 +107,14 @@ def run(self) -> dict:

peft_version = peft.__version__

bitsandbytes_version = "not installed"
if is_bitsandbytes_available():
import bitsandbytes

bitsandbytes_version = bitsandbytes.__version__
quantization_versions = {}
Copy link
Copy Markdown
Collaborator

@DN6 DN6 May 13, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If the backend isn't available, I'd say it's better to skip adding it to the final message entirely. Keeps the logs less noisy.

Copy link
Copy Markdown
Member Author

@sayakpaul sayakpaul May 13, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

for backend_name, is_available_fn, dist_name in _QUANTIZATION_BACKENDS:
if not is_available_fn():
continue
try:
quantization_versions[backend_name] = importlib.metadata.version(dist_name)
except importlib.metadata.PackageNotFoundError:
quantization_versions[backend_name] = "N/A"

xformers_version = "not installed"
if is_xformers_available():
Expand Down Expand Up @@ -162,7 +180,7 @@ def run(self) -> dict:
"Transformers version": transformers_version,
"Accelerate version": accelerate_version,
"PEFT version": peft_version,
"Bitsandbytes version": bitsandbytes_version,
**{f"{name} version": ver for name, ver in quantization_versions.items()},
"Safetensors version": safetensors_version,
"xFormers version": xformers_version,
"Accelerator": accelerator,
Expand Down
Loading