RobertCsordas / moeLinks
Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"
☆38Updated last week
Alternatives and similar repositories for moe
Users that are interested in moe are comparing it to the libraries listed below
Sorting:
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- ☆48Updated last year
- sigma-MoE layer☆19Updated last year
- ☆79Updated 10 months ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆98Updated 8 months ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 9 months ago
- Here we will test various linear attention designs.☆59Updated last year
- This repo is based on https://github.com/jiaweizzhao/GaLore☆28Updated 9 months ago
- ☆53Updated last year
- ☆55Updated 11 months ago
- GoldFinch and other hybrid transformer components☆45Updated 11 months ago
- DPO, but faster 🚀☆43Updated 6 months ago
- ☆53Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- A repository for research on medium sized language models.☆76Updated last year
- ☆51Updated 7 months ago
- ☆45Updated last year
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- ☆44Updated last year
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆48Updated 2 years ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 8 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆55Updated 10 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆32Updated 3 months ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆54Updated last year
- The evaluation framework for training-free sparse attention in LLMs☆69Updated this week
- ☆25Updated last year
- From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…☆47Updated 2 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆70Updated last week
- ☆27Updated last year