Convert Graph to True Integer Representation After PTQ and Optimize Quantizers with Bitshift

This issue focuses on improving the efficiency of the graph after Post-Training Quantization (PTQ) by:

• Casting the graph from fake quantization (floating-point with scaling factors) to a true integer representation.
• Replacing quantizer nodes with bitshift operations when the "single shift approximation" feature is enabled.

Fixed by MR:!46 (merged) This is related to this issue: aidge_backend_cpu#35

added Enhancement ⭐ label

assigned to @noamzerah

mentioned in merge request !35 (closed)

changed the description

mentioned in merge request !46 (merged)

aidge_onnx#61 -> I delved into this topic on the issue for the support of export to ONNX of quantized models.

changed the description

mentioned in issue #24 (closed)

changed milestone to %aidge v0.6.0

changed due date to April 07, 2025

changed milestone to %aidge v0.7.0

closed