pytorch-labs / attention-gym
Helpful tools and examples for working with flex-attention
β460Updated 2 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 Pytorchβ474Updated 2 weeks ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.β473Updated 2 weeks ago
- This repository contains the experimental PyTorch native float8 training UXβ211Updated 3 months ago
- Annotated version of the Mamba paperβ455Updated 8 months ago
- Transformers with Arbitrarily Large Contextβ637Updated 2 months ago
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β190Updated 2 weeks ago
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Coresβ277Updated last month
- Ring attention implementation with flash attentionβ578Updated this week
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793β321Updated last week
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorchβ291Updated 4 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"β212Updated 2 months ago
- β132Updated last year
- Triton-based implementation of Sparse Mixture of Experts.β185Updated 3 weeks ago
- For optimization algorithm research and development.β408Updated this week
- Efficient implementations of state-of-the-art linear attention models in Pytorch and Tritonβ1,320Updated this week
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAIβ234Updated this week
- Some preliminary explorations of Mamba's context scaling.β190Updated 9 months ago
- Accelerated First Order Parallel Associative Scanβ162Updated 2 months ago
- Pipeline Parallelism for PyTorchβ725Updated 2 months ago
- Building blocks for foundation models.β385Updated 10 months ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorchβ242Updated 6 months ago
- β227Updated 2 months ago
- Explorations into some recent techniques surrounding speculative decodingβ209Updated last year
- Understand and test language model architectures on synthetic tasks.β161Updated 6 months ago
- Cataloging released Triton kernels.β132Updated 2 months ago
- [ICML 2024] CLLMs: Consistency Large Language Modelsβ350Updated 3 months ago
- Microsoft Automatic Mixed Precision Libraryβ522Updated last month
- A repository for log-time feedforward networksβ216Updated 7 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMsβ183Updated last month
- A repository for research on medium sized language models.β479Updated this week