Welcome to MIT HAN Lab, where efficiency meets performance, innovation converges with excellence in the realm of artificial intelligence (AI) and computer architecture. Our lab stands at the forefront of cutting-edge research, encompassing a wide spectrum of topics from LLM and genAI to TinyML and hardware design. Combining expertise in algorithm and hardware, we are dedicated to pushing the limits of efficiency in AI.
Graduated PhD students: Ji Lin (OpenAI), Hanrui Wang (assistant professor @UCLA), Zhijian Liu (assistant professor @UCSD), Han Cai (NVIDIA Research), Haotian Tang (Google DeepMind).
Accelerating LLM and Generative AI [slides]:
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.
TorchSparse++ has been adopted by One-2-3-45++ from Prof. Hao Su's lab (UCSD) for 3D object generation!
🔥 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.
TorchSparse++ has been adopted by One-2-3-45 from Prof. Hao Su's lab (UCSD) for 3D mesh reconstruction!
Diffusion models have been proven highly effective at generating high-quality images. However, as these models grow larger, they require significantly more memory and suffer from higher latency, posing substantial challenges for deployment. In this work, we aim to accelerate diffusion models by quantizing their weights and activations to 4 bits. At such an aggressive level, both weights and activations are highly sensitive, where conventional post-training quantization methods for large language models like smoothing become insufficient. To overcome this limitation, we propose SVDQuant, a new 4-bit quantization paradigm. Different from smoothing which redistributes outliers between weights and activations, our approach absorbs these outliers using a low-rank branch. We first consolidate the outliers by shifting them from activations to weights, then employ a high-precision low-rank branch to take in the weight outliers with Singular Value Decomposition (SVD). This process eases the quantization on both sides. However, naïvely running the low-rank branch independently incurs significant overhead due to extra data movement of activations, negating the quantization speedup. To address this, we co-design an inference engine Nunchaku that fuses the kernels of the low-rank branch into those of the low-bit branch to cut off redundant memory access. It can also seamlessly support off-the-shelf low-rank adapters (LoRAs) without the need for re-quantization. Extensive experiments on SDXL, PixArt-∑, and FLUX.1 validate the effectiveness of SVDQuant in preserving image quality. We reduce the memory usage for the 12B FLUX.1 models by 3.5×, achieving 3.0× speedup over the 4-bit weight-only quantized baseline on the 16GB laptop 4090 GPU, paving the way for more interactive applications on PCs. Our quantization library and inference engine are open-sourced.
A new W4A4 quantization paradigm for diffusion models.
FP8 training has emerged as a promising method for improving training efficiency. Existing frameworks accelerate training by applying FP8 computation to linear layers while leaving optimizer states and activations in higher precision, which fails to fully optimize memory usage. This paper introduces COAT (Compressing Optimizer States and Activations for FP8 Training), a novel FP8 training framework designed to significantly reduce memory footprint when training large models. COAT addresses current limitations through two key innovations: (1) Dynamic Range Expansion, which aligns optimizer state distributions more closely with the FP8 representation range, thereby reducing quantization error, and (2) Mixed-Granularity Activation Quantization, which optimizes activation memory using a combination of per-tensor and per-group quantization strategies. Experiments demonstrate that COAT effectively reduces end-to-end training memory footprint by 1.54x compared to BF16 while achieving nearly lossless performance across various tasks, such as Large Language Model pretraining and fine-tuning and Vision Language Model training. COAT also achieves a 1.43x end-to-end training speedup compared to BF16, performing on par with or surpassing TransformerEngine's speedup. COAT enables efficient full-parameter training of large models on fewer GPUs, and facilitates doubling the batch size in distributed training settings, providing a practical solution for scaling large-scale model training.
We propose COAT, a memory efficient FP8 training method for large language models.
We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096×4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU. Core designs include: (1) Deep compression autoencoder: unlike traditional AEs, which compress images only 8×, we trained an AE that can compress images 32×, effectively reducing the number of latent tokens. (2) Linear DiT: we replace all vanilla attention in DiT with linear attention, which is more efficient at high resolutions without sacrificing quality. (3) Decoder-only text encoder: we replaced T5 with modern decoder-only small LLM as the text encoder and designed complex human instruction with in-context learning to enhance the image-text alignment. (4) Efficient training and sampling: we propose Flow-DPM-Solver to reduce sampling steps, with efficient caption labeling and selection to accelerate convergence. As a result, Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput. Moreover, Sana-0.6B can be deployed on a 16GB laptop GPU, taking less than 1 second to generate a 1024×1024 resolution image. Sana enables content creation at low cost. Code and model will be publicly released.
SANA is an efficient linear DiT that can generate images up to 4096 × 4096. SANA delivers: 20x smaller & 100x faster than FLUX; Deployable on laptop GPU; Top-notch GenEval & DPGBench results.
Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache pruning methods either damage the long-context capabilities of LLMs or offer only limited efficiency improvements. In this paper, we identify that only a fraction of attention heads, a.k.a, Retrieval Heads, are critical for processing long contexts and require full attention across all tokens. In contrast, all other heads, which primarily focus on recent tokens and attention sinks, referred to as Streaming Heads, do not require full attention. Based on this insight, we introduce DuoAttention, a framework that only applies a full KV cache to retrieval heads while using a light-weight, constant-length KV cache for streaming heads, which reduces both LLM's decoding and pre-filling memory and latency without compromising its long-context abilities. DuoAttention uses a lightweight, optimization-based algorithm with synthetic data to identify retrieval heads accurately. Our method significantly reduces long-context inference memory by up to 2.55x for MHA and 1.67x for GQA models while speeding up decoding by up to 2.18x and 1.50x and accelerating pre-filling by up to 1.73x and 1.63x for MHA and GQA models, respectively, with minimal accuracy loss compared to full attention. Notably, combined with quantization, DuoAttention enables Llama-3-8B decoding with 3.3 million context length on a single A100 GPU.
By selectively applying full attention to critical attention heads and using "Streaming Attention" on others, DuoAttention significantly reduces both pre-filling and decoding memory usage and latency for long-context LLMs, while maintaining their long-context capabilities.
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.
