[NeurIPS 2022] “M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design”, Hanxue Liang*, Zhiwen Fan*, Rishov Sarkar, Ziyu Jiang, Tianlong Chen, Kai Zou, Yu Cheng, Cong Hao, Zhangyang Wang
☆136Nov 30, 2022Updated 3 years ago
Alternatives and similar repositories for M3ViT
Users that are interested in M3ViT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts☆140May 10, 2024Updated 2 years ago
- ☆53Aug 28, 2024Updated last year
- ☆717Dec 6, 2025Updated 5 months ago
- Soft Mixture of Experts Vision Transformer, addressing MoE limitations as highlighted by Puigcerver et al., 2023.☆16Aug 13, 2023Updated 2 years ago
- Deep learning accelerator for convolutional layer (convolution operation) and fully-connected layer(matrix-multiplication).☆20Nov 18, 2018Updated 7 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- A co-design architecture on sparse attention☆55Aug 23, 2021Updated 4 years ago
- An FPGA Accelerator for Transformer Inference☆93Apr 29, 2022Updated 4 years ago
- Research and Materials on Hardware implementation of Transformer Model☆308Feb 28, 2025Updated last year
- ☆19Mar 21, 2023Updated 3 years ago
- Implementation of AAAI 2022 Paper: Go wider instead of deeper☆32Oct 27, 2022Updated 3 years ago
- SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration (Full Paper Accepted in FPGA'24)☆36Mar 12, 2026Updated 2 months ago
- [DATE 2025] Official implementation and dataset of AIrchitect v2: Learning the Hardware Accelerator Design Space through Unified Represen…☆19Jan 17, 2025Updated last year
- HW/SW co-design of sentence-level energy optimizations for latency-aware multi-task NLP inference☆54Mar 24, 2024Updated 2 years ago
- [TCAD 2021] Block Convolution: Towards Memory-Efficient Inference of Large-Scale CNNs on FPGA☆17Jul 7, 2022Updated 3 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A fusion model of transformer and CNN for remote sensing image classification. Datasets Used: UCM, RSSCN7☆11May 29, 2025Updated 11 months ago
- [NeurIPS 2023] ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer☆30Dec 6, 2023Updated 2 years ago
- This repository contains the hardware implementation for Static BFP convolution on FPGA☆10Oct 15, 2019Updated 6 years ago
- [TECS'23] A project on the co-design of Accelerators and CNNs.☆21Dec 10, 2022Updated 3 years ago
- ☆95Apr 3, 2023Updated 3 years ago
- [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning☆131Aug 27, 2024Updated last year
- An up-to-date list of works on Multi-Task Learning☆378Mar 2, 2026Updated 2 months ago
- This is the official repository for our NeurIPS'22 paper "Watermarking for Out-of-distribution Detection."☆18Feb 24, 2023Updated 3 years ago
- A new multi-task learning framework using Vision Transformers☆11Jun 19, 2024Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- The framework for the paper "Inter-layer Scheduling Space Definition and Exploration for Tiled Accelerators" in ISCA 2023.☆83Mar 12, 2025Updated last year
- ☆30Dec 12, 2022Updated 3 years ago
- Post-Training Quantization for Vision transformers.☆242Jul 19, 2022Updated 3 years ago
- ☆16Oct 20, 2025Updated 7 months ago
- [WACV'23] Mixture Outlier Exposure for Out-of-Distribution Detection in Fine-grained Environments☆26Apr 12, 2023Updated 3 years ago
- ☆27Apr 11, 2023Updated 3 years ago
- PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538☆1,243Apr 19, 2024Updated 2 years ago
- McPAT modeling framework☆12Oct 18, 2014Updated 11 years ago
- This repository contains papers for a comprehensive survey on accelerated generation techniques in Large Language Models (LLMs).☆11May 24, 2024Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- An efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences☆32Mar 7, 2024Updated 2 years ago
- 哈尔滨工业大学（深圳）2021年球季学期深度学习体系结构实验☆17Oct 1, 2022Updated 3 years ago
- LSTM neural network (verilog)☆16Dec 5, 2018Updated 7 years ago
- Code for "CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction" on CIFAR-10/100.☆14Dec 10, 2021Updated 4 years ago
- PyTorch implementation of LIMoE☆52Apr 1, 2024Updated 2 years ago
- FPGA based Vision Transformer accelerator (Harvard CS205)☆156Feb 11, 2025Updated last year
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆859Sep 13, 2023Updated 2 years ago