Sayak Paul
Machine Learning Engineer, Hugging Face | Diffusers & Edge AI Specialist | Google Developer Expert
Machine Learning Engineer at Hugging Face and Google Developer Expert in Machine Learning. Key maintainer of huggingface/diffusers, specializing in edge optimization, low-bit quantization (bitsandbytes, AWQ), diffusion distillation (SDXL-Turbo, LCM), and diffusion fine-tuning. Authored dozens of widely read open-source technical tutorials and benchmarks democratizing generative vision models.
Areas of focus
Professional niches
Proof of Work
Optimizing Latent Diffusion Models for Edge & Mobile Deployment
Authored comprehensive engineering benchmarks and guides demonstrating INT8 and FP16 quantization, TensorRT compilation, and CoreML conversion for running diffusion pipelines on consumer hardware.
Quantization below 8-bit precision requires calibration against representative prompt distributions to prevent latent vector drift.
Context: TensorRT, Core ML, ONNX, mobile inference constraints.
View missionDiffusion Model Distillation & Latent Consistency Optimization
Co-authored and integrated Latent Consistency Model (LCM) LoRA adapters into Hugging Face Diffusers, compressing multi-step diffusion sampling into 2 to 4 inference steps for real-time generation.
Aggressive 2-step distillation can introduce subtle high-frequency smoothing in photorealistic background details.
Context: PyTorch, CUDA, LCM-LoRA, SDXL, Apple Silicon Metal.
View mission