Alex Kogan 89342ce4c0 [Quantization] [Performance] Enable Marlin GEMM kernels for the calibration-free RTN-based quantization (#26051) ...

Signed-off-by: Alex Kogan <alex.kogan@oracle.com>
Signed-off-by: Alex Kogan <82225080+sakogan@users.noreply.github.com>

2025-10-13 18:52:54 +00:00

..

layers

[Quantization] [Performance] Enable Marlin GEMM kernels for the calibration-free RTN-based quantization (#26051)

2025-10-13 18:52:54 +00:00

model_loader

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

models

[Model] Use merge_by_field_config for MM models (M-N) (#26710)

2025-10-14 01:27:01 +08:00

warmup

[UX] Speedup DeepGEMM warmup with heuristics (#25619)

2025-10-13 07:59:27 -07:00

__init__.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

custom_op.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

parameter.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00