google-research / vmoeLinks
☆702Updated 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 GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4☆960Updated last month
- A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models☆846Updated 2 years ago
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆505Updated last year
- A method to increase the speed and lower the memory footprint of existing vision transformers.☆1,166Updated last year
- Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models☆806Updated 7 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆378Updated last year
- Official code for our CVPR'22 paper “Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space”☆251Updated 5 months ago
- A curated reading list of research in Mixture-of-Experts(MoE).☆658Updated last year
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆343Updated 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☆1,224Updated last year
- Lossless Training Speed Up by Unbiased Dynamic Data Pruning☆344Updated last year
- iBOT : Image BERT Pre-Training with Online Tokenizer (ICLR 2022)☆762Updated 3 years ago
- A fast MoE impl for PyTorch☆1,829Updated 11 months ago
- CLIP-like model evaluation☆800Updated 2 weeks ago
- Official Open Source code for "Scaling Language-Image Pre-training via Masking"☆427Updated 2 years ago
- [NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification☆647Updated 2 years ago
- Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper☆780Updated 3 years ago
- Implementation of "Attention Is Off By One" by Evan Miller☆198Updated 2 years ago
- Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"☆372Updated 2 years ago
- TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.☆1,691Updated this week
- Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)☆939Updated 2 years ago
- A collection of AWESOME things about mixture-of-experts☆1,258Updated last year
- Robust fine-tuning of zero-shot models☆759Updated 3 years ago
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm☆673Updated 3 years ago
- This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."☆227Updated 2 years ago
- ☆285Updated 5 months ago
- A general and accurate MACs / FLOPs profiler for PyTorch models☆635Updated 6 months ago
- (Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from …☆190Updated last year
- ☆293Updated last year
- [CVPR 2023 Highlight] This is the official implementation of "Stitchable Neural Networks".☆250Updated 2 years ago