pytorch-labs / attention-gym
Helpful tools and examples for working with flex-attention
β469Updated 3 weeks ago
Related projects β
Alternatives and complementary repositories for attention-gym
- Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorchβ476Updated 3 weeks ago
- Annotated version of the Mamba paperβ457Updated 8 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.β483Updated 3 weeks ago
- This repository contains the experimental PyTorch native float8 training UXβ211Updated 3 months ago
- Transformers with Arbitrarily Large Contextβ641Updated 3 months ago
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β193Updated this week
- Ring attention implementation with flash attentionβ585Updated last week
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorchβ293Updated 5 months ago
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Coresβ281Updated last month
- Triton-based implementation of Sparse Mixture of Experts.β185Updated last month
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"β214Updated 3 months ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793β328Updated 3 weeks ago
- Pipeline Parallelism for PyTorchβ726Updated 2 months ago
- β132Updated last year
- Understand and test language model architectures on synthetic tasks.β162Updated 6 months ago
- Building blocks for foundation models.β394Updated 10 months ago
- Some preliminary explorations of Mamba's context scaling.β191Updated 9 months ago
- Efficient implementations of state-of-the-art linear attention models in Pytorch and Tritonβ1,339Updated this week
- β228Updated 2 months ago
- Accelerated First Order Parallel Associative Scanβ163Updated 3 months ago
- Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parametersβ335Updated last week
- Cataloging released Triton kernels.β134Updated 2 months ago
- Applied AI experiments and examples for PyTorchβ166Updated 2 weeks ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorchβ246Updated 6 months ago
- Microsoft Automatic Mixed Precision Libraryβ525Updated last month
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorchβ571Updated last week
- For optimization algorithm research and development.β449Updated this week
- π Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.β165Updated this week
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ353Updated this week
- Explorations into some recent techniques surrounding speculative decodingβ211Updated last year