Home Original page

ashahba - Overview

Skip to content

Navigation Menu

Sign in

Appearance settings

View ashahba's full-sized avatar

Abolfazl Shahbazi ashahba

Senior AI Frameworks Engineer

  • Portland, OR

Block or report ashahba

Pinned Loading

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

    Python 2.6k 302