lucidrains / ring-attention-pytorchLinks
Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch
☆529Updated last month
Alternatives and similar repositories for ring-attention-pytorch
Users that are interested in ring-attention-pytorch are comparing it to the libraries listed below
Sorting:
- Large Context Attention☆718Updated 5 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆255Updated this week
- Helpful tools and examples for working with flex-attention☆865Updated 2 weeks ago
- Ring attention implementation with flash attention☆800Updated last week
- ☆485Updated this week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆561Updated 3 weeks ago
- This repository contains the experimental PyTorch native float8 training UX☆224Updated 11 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆237Updated last month
- Triton-based implementation of Sparse Mixture of Experts.☆224Updated 7 months ago
- [ICML 2024] CLLMs: Consistency Large Language Models☆396Updated 7 months ago
- Microsoft Automatic Mixed Precision Library☆612Updated 9 months ago
- Annotated version of the Mamba paper☆486Updated last year
- 🔥 A minimal training framework for scaling FLA models☆188Updated last month
- LLM KV cache compression made easy☆535Updated this week
- Scalable toolkit for efficient model reinforcement☆478Updated this week
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆345Updated last year
- Megatron's multi-modal data loader☆217Updated this week
- Some preliminary explorations of Mamba's context scaling.☆214Updated last year
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆287Updated last month
- Pipeline Parallelism for PyTorch☆769Updated 10 months ago
- Official PyTorch implementation of QA-LoRA☆138Updated last year
- Muon is an optimizer for hidden layers in neural networks☆988Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆735Updated 9 months ago
- ☆191Updated this week
- Understand and test language model architectures on synthetic tasks.☆219Updated last month
- Applied AI experiments and examples for PyTorch☆281Updated last month
- A repository for research on medium sized language models.☆502Updated last month
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆212Updated 10 months ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆124Updated 10 months ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆427Updated 2 months ago