lucidrains / ring-attention-pytorchLinks
Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorch
β532Updated 2 months ago
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 Attentionβ719Updated 6 months ago
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β258Updated last week
- Helpful tools and examples for working with flex-attentionβ904Updated 2 weeks ago
- Ring attention implementation with flash attentionβ828Updated last week
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.β565Updated this week
- β506Updated this week
- This repository contains the experimental PyTorch native float8 training UXβ224Updated last year
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ397Updated 8 months ago
- π₯ A minimal training framework for scaling FLA modelsβ209Updated last month
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793β431Updated 2 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"β238Updated last month
- Triton-based implementation of Sparse Mixture of Experts.β230Updated 8 months ago
- Annotated version of the Mamba paperβ487Updated last year
- Scalable toolkit for efficient model reinforcementβ558Updated this week
- Microsoft Automatic Mixed Precision Libraryβ616Updated 10 months ago
- Some preliminary explorations of Mamba's context scaling.β216Updated last year
- Explorations into some recent techniques surrounding speculative decodingβ275Updated 7 months ago
- LLM KV cache compression made easyβ560Updated this week
- Normalized Transformer (nGPT)β185Updated 8 months ago
- A repository for research on medium sized language models.β506Updated last month
- Megatron's multi-modal data loaderβ230Updated last week
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorchβ352Updated last year
- PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attentionβ¦β290Updated last year
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.β739Updated 10 months ago
- π³ Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"β731Updated 4 months ago
- Understand and test language model architectures on synthetic tasks.β221Updated 2 weeks ago
- Pipeline Parallelism for PyTorchβ775Updated 11 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"β244Updated 6 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAIβ288Updated last month
- Scalable and Performant Data Loadingβ290Updated last week