Skip to content

Replace WeightOnlyInt8Linear with TorchAO int8_weight_only quantization #3328

Replace WeightOnlyInt8Linear with TorchAO int8_weight_only quantization

Replace WeightOnlyInt8Linear with TorchAO int8_weight_only quantization #3328

Annotations

1 warning

test-gpu-aoti-float32 (cuda, stories15M)  /  linux-job

succeeded Nov 12, 2024 in 13m 17s