pymllm.backends.qualcomm.transformers.core.qdq¶

Classes¶

ActivationQDQ

General activation Quantization-DeQuantization (QDQ) module.

Module Contents¶

class pymllm.backends.qualcomm.transformers.core.qdq.ActivationQDQ(bits=8, qscheme=torch.per_tensor_affine)¶

Bases: torch.nn.Module

General activation Quantization-DeQuantization (QDQ) module. Supports both Symmetric and Asymmetric (Affine) quantization. Uses torch.qint32 as a unified type to support various bit-widths.

bits = 8¶

qscheme¶

dtype¶

fake_quant¶

forward(x)¶

enable_observer()¶: Enable tracking of min/max values to update scale and zero_point.

disable_observer()¶: Freeze scale and zero_point calculation.

enable_fakequant()¶: Enable simulation of quantization error.

disable_fakequant()¶: Disable quantization simulation (act as identity).

extra_repr()¶