Pruning

PQuant: Streamlining ML Model Compression to Deployment for Next-Gen Detector Systems featured image

PQuant: Streamlining ML Model Compression to Deployment for Next-Gen Detector Systems

PQuant/PQuantML: config-driven pruning + quantization pipeline (PyTorch/TensorFlow) with hardware-aware MDMM optimization; aimed at FPGA/ASIC deployment workflows (hls4ml …

avatar
Arghya Ranjan Das