SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

Low Precision Arithmetic Simulation in PyTorch

A script to convert floating-point CNN models into generalized low-precision ShiftCNN representation

Low Precision(quantized) Yolov5

CUDA/HIP header-only library for low-precision (16 bit, 8 bit) and vectorized GPU kernel development

JAX Scalify: end-to-end scaled arithmetics

Code for DNN feature map compression paper

Small utility library

Implemented post-training quantisation (PTQ) on transformer-based reasoning models using 8-bit and 4-bit weight quantisation (INT8, INT4) with frameworks like PyTorch and Hugging Face Transformers. Leveraged libraries such as bitsandbytes to reduce model size and accelerate inference, while evaluating performance degradation on reasoning tasks. Com

QuantLab-8bit is a reproducible benchmark of 8-bit quantization on compact vision backbones. It includes FP32 baselines, PTQ (dynamic & static), QAT, ONNX exports, parity checks, ORT CPU latency, and visual diagnostics.

LinearCosine: Adding beats multiplying for lower-precision efficient cosine similarity

Probabilistic GEMM verification for ML kernels — Freivalds algorithm, PyTorch, cross-backend (CUDA / MPS / ROCm).