xudoong / EdgeVisionTransformer
To deploy Transformer models in CV to mobile devices.
☆17Updated 3 years ago
Alternatives and similar repositories for EdgeVisionTransformer:
Users that are interested in EdgeVisionTransformer are comparing it to the libraries listed below
- This is a list of awesome edgeAI inference related papers.☆95Updated last year
- [CVPRW 2021] Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms☆29Updated 2 years ago
- GPU operators for sparse tensor operations☆31Updated last year
- The open-source project for "Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading"[MobiCom'2022]☆18Updated 2 years ago
- Post-training sparsity-aware quantization☆34Updated 2 years ago
- Official implementation of the EMNLP23 paper: Outlier Suppression+: Accurate quantization of large language models by equivalent and opti…☆47Updated last year
- Code for paper "ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection" (MobiSys'23)☆12Updated last year
- Manually implemented quantization-aware training☆21Updated 2 years ago
- ☆35Updated 2 years ago
- MobiSys#114☆21Updated last year
- The official PyTorch implementation of the NeurIPS2022 (spotlight) paper, Outlier Suppression: Pushing the Limit of Low-bit Transformer L…☆48Updated 2 years ago
- BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.☆51Updated 2 years ago
- [ICML 2023] This project is the official implementation of our accepted ICML 2023 paper BiBench: Benchmarking and Analyzing Network Binar…☆55Updated last year
- ☆10Updated 2 months ago
- An external memory allocator example for PyTorch.☆14Updated 3 years ago
- ☆25Updated 3 years ago
- Code for ICML 2021 submission☆34Updated 4 years ago
- ☆29Updated last year
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆94Updated 2 years ago
- ☆77Updated last year
- ☆65Updated 3 months ago
- ☆19Updated 5 months ago
- [ECCV 2022] SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning☆19Updated 2 years ago
- Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".☆113Updated last year
- BitSplit Post-trining Quantization☆49Updated 3 years ago
- PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices☆29Updated last year
- [NeurIPS 2023] ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer☆32Updated last year
- ☆68Updated 2 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆91Updated this week
- Code for our paper at ECCV 2020: Post-Training Piecewise Linear Quantization for Deep Neural Networks☆68Updated 3 years ago