google-research / vmoeLinks
☆656Updated last month
Alternatives and similar repositories for vmoe
Users that are interested in vmoe are comparing it to the libraries listed below
Sorting:
- Tutel MoE: Optimized Mixture-of-Experts Library, Support DeepSeek/Kimi-K2/Qwen3 FP8/FP4☆870Updated last week
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆788Updated last year
- A method to increase the speed and lower the memory footprint of existing vision transformers.☆1,079Updated last year
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆477Updated last year
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆352Updated last year
- Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”☆250Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆309Updated 4 months ago
- A curated reading list of research in Mixture-of-Experts(MoE).☆639Updated 9 months ago
- PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538☆1,149Updated last year
- Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models☆797Updated last month
- iBOT : Image BERT Pre-Training with Online Tokenizer (ICLR 2022)☆739Updated 3 years ago
- A fast MoE impl for PyTorch☆1,769Updated 5 months ago
- Implementation of "Attention Is Off By One" by Evan Miller☆193Updated last year
- Official Open Source code for "Scaling Language-Image Pre-training via Masking"☆426Updated 2 years ago
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆368Updated last year
- Lossless Training Speed Up by Unbiased Dynamic Data Pruning☆339Updated 10 months ago
- Implementation of a memory efficient multi-head attention as proposed in the paper, "Self-attention Does Not Need O(n²) Memory"☆379Updated 2 years ago
- Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)☆920Updated last year
- CLIP-like model evaluation☆743Updated last week
- A general and accurate MACs / FLOPs profiler for PyTorch models☆624Updated last week
- Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper☆768Updated 2 years ago
- [NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification☆619Updated 2 years ago
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm☆663Updated 2 years ago
- Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch☆532Updated 2 months ago
- Transformer based on a variant of attention that is linear complexity in respect to sequence length☆793Updated last year
- ☆604Updated last month
- ☆279Updated 2 years ago
- Robust fine-tuning of zero-shot models☆725Updated 3 years ago
- DataComp: In search of the next generation of multimodal datasets☆729Updated 3 months ago
- This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."☆227Updated last year