Dr. Song Han
MIT / HAN Lab
Verified Proof of Work Artifacts
2 items catalogedEach 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.
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.
Requires support for per-token dynamic scaling or fixed calibration scale tensors in runtime engines.
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.
Requires representative calibration datasets to accurately identify activation outliers across specialized domains.