SVDQuant supports NVFP4 on NVIDIA Blackwell GPUs with 3× speedup over BF16 and better image quality than INT4. Try our interactive demo below or at https://svdquant.mit.edu/! Our code is all available at https://github.com/mit-han-lab/nunchaku.

With the arrival of the RTX 5090, we built a high-performance workstation to maximize its AI computing potential. In this blog post, we share our experience—from overcoming setup challenges to testing its performance.

Explore the latest advancement in TinyChat – the 2.0 version with significant advancements in prefilling speed of Edge LLMs and VLMs. Apart from the 3-4x decoding speedups achieved with AWQ quantization, TinyChat 2.0 now delivers state-of-the-art Time-To-First-Token, which is 1.5-1.7x faster than the legacy version of TinyChat.

A new post-training training quantization paradigm for diffusion models, which quantize both the weights and activations of FLUX.1 to 4 bits, achieving 3.5× memory and 8.7× latency reduction on a 16GB laptop 4090 GPU. Code: https://www.github.com/mit-han-lab/nunchaku

We introduce Block Sparse Attention, a library of sparse attention kernels that supports various sparse patterns, including streaming attention with token granularity, streaming attention with block granularity, and block-sparse attention. By incorporating these patterns, Block Sparse Attention can significantly reduce the computational costs of LLMs, thereby enhancing their efficiency and scalability. We release the implementation of Block Sparse Attention, which is modified based on FlashAttention 2.4.2.

Explore the latest advancement in TinyChat and AWQ – the integration of Visual Language Models (VLM) on the edge! The exciting advancements in VLM allows LLMs to comprehend visual inputs, enabling seamless image understanding tasks like caption generation, question answering, and more. With the latest release, TinyChat now supports leading VLMs such as VILA, which can be easily quantized with AWQ, empowering users with seamless experience for image understanding tasks.

In this blog, we introduce DistriFusion, a training-free algorithm to harness multiple GPUs to accelerate diffusion model inference without sacrificing image quality. It can reduce SDXL latency by up to 6.1× on 8 A100s. Our work has been accepted by CVPR 2024 as a highlight. Code: https://github.com/mit-han-lab/distrifusion

Running large language models (LLMs) on the edge is of great importance. In this blog, we introduce TinyChat, an efficient and lightweight system for LLM deployment on the edge. It runs Meta's latest LLaMA-2 model at 30 tokens / second on NVIDIA Jetson Orin and can easily support different models and hardware.

In MCUNetV3, we enable on-device training under 256KB SRAM and 1MB Flash, using less than 1/1000 memory of PyTorch while matching the accuracy on the visual wake words application. It enables the model to adapt to newly collected sensor data and users can enjoy customized services without uploading the data to the cloud thus protecting privacy.