Welcome to MIT HAN Lab! We specialize in efficient generative AI, including large language models (LLMs), multi-modal models, and diffusion models. Today’s foundation models are remarkably powerful but prohibitively costly in terms of computation, energy, and scalability. At MIT HAN Lab, we integrate algorithm–system co-design to push the frontier of AI efficiency and performance. Our research focuses on the infrastructure of the entire AI stack — from pre-training and post-training to model compression, deployment and token factory — bridging fundamental breakthroughs with real-world applications. By rethinking how AI is designed with GPU efficiency in mind, we aim to make generative AI faster, greener, and more accessible.
PI: Prof. Song Han
Alumni: Ji Lin (OpenAI -> Meta TBD lab), Hanrui Wang (Co-founder @Eigen AI, acquired by Nebius, SVP of applied AI), Zhijian Liu (Assistant professor @UCSD; co-founder @Inco AI), Han Cai (NVIDIA Research), Haotian Tang (Google Deepmind->Meta TBD lab), Yujun Lin (NVIDIA Research -> Co-founder @Nunchux AI), Wei-Chen Wang (Co-Founder @Eigen AI, acquired by Nebius, VP of AI Inference), Wei-Ming Chen (NVIDIA), Muyang Li (Co-founder @Nunchux AI), Zhekai Zhang (Co-founder @Nunchux AI), Guangxuan Xiao (Thinking Machines Lab)
Accelerating LLM and Generative AI [slides]:
Kernel Design Agents (KDA) achieves 1st place in the MoE Track, 2nd place in the DSA Track, and 3rd place in the GDN Track at the MLSys 2026 FlashInfer Full-Agent Track!
HART has been highlighted by MIT news: AI tool generates high-quality images faster than state-of-the-art approaches!
🔥⚡ We release TinyChat 2.0, the latest version with significant advancements in prefilling speed of Edge LLMs and VLMs, 1.5-1.7x faster than the previous version of TinyChat. Please refer to our blog for more details.
DistriFusion is integrated in NVIDIA's TensorRT-LLM for distributed inference on high-resolution image generation.
🔥 NVIDIA TensorRT-LLM, AMD, Google Vertex AI, Amazon Sagemaker, Intel Neural Compressor, FastChat, vLLM, HuggingFace TGI, and LMDeploy adopt AWQ to improve LLM serving efficiency. Our AWQ models on HuggingFace has received over 6 million downloads.
Congrats on graduation! Cheers on the next move: Zhijian Liu: assistant professor at UCSD, Hanrui Wang: assistant professor at UCLA, Ji Lin: OpenAI, Han Cai: NVIDIA Research, Wei-Chen Wang (postdoc): Amazon, Wei-Ming Chen (postdoc): NVIDIA.
We show SmoothQuant can enable W8A8 quantization for Llama-1/2, Falcon, Mistral, and Mixtral models with negligible loss.
We supported VILA Vision Languague Models in AWQ & TinyChat! Check our latest demos with multi-image inputs!
StreamingLLM is integrated by HPC-AI Tech SwiftInfer to support infinite input length for LLM inference.
StreamingLLM is integrated by CMU, UW, and OctoAI, enabling endless and efficient LLM generation on iPhone!
Congrats Ji Lin completed and defended his PhD thesis: "Efficient Deep Learning Computing: From TinyML to Large Language Model". Ji joined OpenAI after graduation.
AWQ is integrate by NVIDIA TensorRT-LLM, can fit Falcon-180B on a single H200GPU with INT4 AWQ, and 6.7x faster Llama-70B over A100.
🔥 AWQ is now integrated natively in Hugging Face transformers through from_pretrained. You can either load quantized models from the Hub or your own HF quantized models.
Attention Sinks, an library from community enables StreamingLLM on more Huggingface LLMs. blog.
A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoning accuracy and inference efficiency can be challenging, as the two objectives can favor different reasoning behaviors. Independently post-trained models already offer distinct strengths in accuracy and efficiency. We introduce Lightning Weave, a post-training framework that extracts and composes these independently learned capabilities in a single student through on-policy distillation. Each acquired capability is represented by the policy shift from the model before post-training to the resulting specialist. Lightning Weave combines aligned log-ratio shifts at shared student token states and uses Tilted-Target DOPD to convert the cached signals into a stable learning target. Each anchor pair scores the cached trajectories once, enabling subsequent student training without serving multiple live anchor models concurrently. Across diverse student models and benchmarks in mathematics and code, Lightning Weave substantially improves upon the base students and achieves a state-of-the-art accuracy-efficiency frontier. On Qwen3.5-4B, it raises HMMT 2025 accuracy from 59.2% to 64.0% with 10.7% fewer response tokens, and LiveCodeBench v5 accuracy from 41.7% to 54.2% with 9.6% fewer response tokens. Adjusting the relative strengths of the anchor signals yields a strong empirical accuracy-efficiency Pareto frontier. These results establish Lightning Weave as a new practical route to efficient reasoning through capability composition.
Lightning Weave improves the accuracy-efficiency frontier of large reasoning models by composing capabilities from accuracy- and efficiency-oriented teachers into a single student through offline distillation.
On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning that the model providing OPD supervision should also have generated the demonstrations used to train the supervised fine-tuning (SFT) reference. However, this condition is frequently violated in practice when SFT data have mixed or unknown provenance or when different models are preferred for SFT data generation and subsequent distillation. In such cross-teacher settings, even a stronger OPD teacher can yield little improvement over the SFT reference. We find that raw teacher--reference disagreement contains potentially useful context-specific teacher evidence as well as a recurring component associated with differences in wording, formatting, and reasoning cadence. We introduce Lightning OPD 2.0 with cross-fitted style residualization, which uses rollout-level cross-fitting to estimate this recurring component as an operational proxy for style-token bias and subtracts it before constructing the token-level OPD update. Across mathematical reasoning and code generation benchmarks, Lightning OPD 2.0 consistently outperforms Lightning OPD in cross-teacher settings. Starting from Klear-Reasoner-8B-SFT, Lightning OPD 2.0 reaches 82.4% on AIME 2024 and 63.0% on LiveCodeBench v5. Together, these results establish Lightning OPD 2.0 as a practical approach to cross-teacher OPD, relaxing teacher consistency as a prerequisite and allowing the SFT data generator and distillation teacher to be selected independently.
Lightning OPD 2.0 enables effective cross-teacher on-policy distillation by mitigating style bias through cross-fitted residualization, allowing the SFT data generator and distillation teacher to be chosen independently.
Despite rapid progress in auto-regressive video diffusion, we identify an emerging system–algorithm bottleneck that limits both deployability and capability: KV-cache memory. In auto-regressive video generation models, the KV-cache grows with history and rapidly dominates GPU memory (often ≥ 30 GB), blocking deployment on widely available hardware. More importantly, memory-bounded KV budgets force small working memory, which directly degrades long-horizon consistency in identity, layout, and motion, etc. To bridge this gap, we present Quant VideoGen (QVG), a training-free KV-cache quantization framework for auto-regressive video diffusion model. QVG exploits video’s spatiotemporal redundancy through Semantic-Aware Smoothing to produce low-magnitude, quantization-friendly residuals. QVG further propose Progressive Residual Quantization, a coarse-to-fine multi-stage scheme that reduces quantization error while enabling a smooth quality–memory trade-off. Across LongCat-Video, HY-WorldPlay, and Self-Forcing, QVG establishes a new Pareto quality-memory frontier, reducing KV memory by up to 7.0× with < 4% end-to-end latency overhead and significantly better quality over baselines.
A training-free KV-cache quantization framework for auto-regressive video diffusion, cutting KV memory by up to 7.0× with under 4% end-to-end latency overhead.
Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications. However, post-training of large diffusion models is still challenging due to the prohibitive memory footprints and slow training speed, which existing parameter-efficient fine-tuning methods only partially address. To overcome these limitations, we propose FourTune, an efficient post-training framework for diffusion models based on an end-to-end W4A4G4 paradigm. FourTune introduces a triple-branch hybrid pipeline that augments the standard LoRA architecture with a frozen numerical stabilizer to isolate quantization-sensitive outliers, enabling stable training under native 4-bit computation. In addition, FourTune employs hardware-efficient block-wise quantization and customized fused kernels to support efficient quantized backpropagation and reduce memory bandwidth overhead. Across customization, reinforcement learning, and distillation tasks, FourTune matches the quality of full-precision fine-tuning. On FLUX.1-dev (12B), FourTune reduces memory overhead by 2.25× and increases end-to-end training throughput by 2.27× compared to BF16 LoRA.
An end-to-end W4A4G4 post-training framework for diffusion models, cutting memory 2.25× and boosting training throughput 2.27× over BF16 LoRA on FLUX.1-dev.
We actively collaborate with industry partners on efficient AI, model compression and acceleration. Our research has influenced and landed in many industrial products: Intel OpenVino, Intel Neural Network Distiller, Intel Neural Compressor, Apple Neural Engine, NVIDIA Sparse Tensor Core, NVIDIA TensorRT LLM, AMD-Xilinx Vitis AI, Qualcomm AI Model Efficiency Toolkit (AIMET), Amazon AutoGluon, Facebook PyTorch, Microsoft NNI, SONY Neural Architecture Search Library, SONY Model Compression Toolkit, ADI MAX78000/MAX78002 Model Training and Synthesis Tool.
