[KongchangAI]
ConceptPTQ / Post-Training Quantization

Post-Training Quantization

Compression performed by directly rounding or calibrating the weights of an already trained model; the model is not optimized for low precision, which can lead to accuracy loss.

Core Facts

Timeline (last 90 days)

Nov 18

DAQ (Decision-Aligned Post-Training Quantization) is a post-training quantization method for spiking Transformers that calibrates the quantizer to align neuron firing decisions.

Unverified50%
Nov 9

Calibration is a key step in post-training quantization (PTQ), using a small batch of representative samples to compute the dynamic range or distribution of activations at each layer in order to determine quantization parameters.

Unverified50%
Oct 14

Post-hoc quantization usually causes noticeable performance degradation at small bit widths, whereas QAT simulates quantization errors during training to maintain low-precision output quality.

Verified80%
Sep 11

Using quantized versions (such as Q4, Q5) can significantly reduce VRAM usage with minimal performance loss.

Verified85%

All Facts (7)

Source Articles