Dr. Song Han
VERIFIED TECHNICAL DOSSIERSources checked

Dr. Song Han

MIT / HAN Lab

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Dr. Song Han. Every entry undergoes editorial source verification.

#1
RESEARCH Checked Sep 21, 2026

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Invented SmoothQuant, an algorithm that mathematically splits quantization difficulty between activations and weights via per-channel scaling transformations, unlocking 8-bit weight and activation (W8A8) tensor-core acceleration.

Model & Execution Context:INT8 matrix multiplications on NVIDIA Ampere/Ada Lovelace tensor cores.
Scope & Limitations

Requires support for per-token dynamic scaling or fixed calibration scale tensors in runtime engines.

#2
RESEARCH Checked Sep 21, 2026

AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration

Published the MLSys Best Paper proving that protecting the top 1% of salient weight channels based on activation magnitudes enables hardware-friendly 4-bit weight-only quantization without costly backpropagation or retraining.

Model & Execution Context:4-bit integer weights, FP16 activations, evaluated across LLaMA-1/2, Vicuna, StarCoder.
Scope & Limitations

Requires representative calibration datasets to accurately identify activation outliers across specialized domains.