Skip to content

Rename coreai-opt export backend to CoreAI #35

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

Merged
pkmandke merged 1 commit into from
Jun 13, 2026
+3 −3
Merged

Rename coreai-opt export backend to CoreAI #35

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions python/src/coreai_models/export/compression.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,7 +122,7 @@ def quantize_pytorch_model(
calibration_data_fn: Optional function that returns calibration data samples.
Required when calibrate_activations is enabled.
export_backend: Backend for the finalized quantized model.
Defaults to ExportBackend.MLIR if not specified.
Defaults to ExportBackend.CoreAI if not specified.

Returns:
Quantized model ready for the specified export backend.
Expand All @@ -135,7 +135,7 @@ def quantize_pytorch_model(
_require_coreai_opt()

if export_backend is None:
export_backend = ExportBackend.MLIR
export_backend = ExportBackend.CoreAI

run_calibration = quantization_config.pop("calibrate_activations", False)
config = QuantizerConfig.from_dict({"quantization_config": quantization_config})
Expand Down Expand Up @@ -240,7 +240,7 @@ def palettize_pytorch_model(
palettizer = KMeansPalettizer(model, config)
prepared_model = palettizer.prepare(example_inputs=example_inputs, num_workers=32)

finalized_model = palettizer.finalize(prepared_model, backend=ExportBackend.MLIR)
finalized_model = palettizer.finalize(prepared_model, backend=ExportBackend.CoreAI)

logger.info("Palettization with coreai-opt complete")
return finalized_model