meta-pytorch / attention-gymLinks
Helpful tools and examples for working with flex-attention
β951Updated 2 weeks ago
Alternatives and similar repositories for attention-gym
Users that are interested in attention-gym are comparing it to the libraries listed below
Sorting:
- Implementation of π Ring Attention, from Liu et al. at Berkeley AI, in Pytorchβ536Updated 3 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.β574Updated 3 weeks ago
- β518Updated last month
- Muon is an optimizer for hidden layers in neural networksβ1,640Updated last month
- Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paperβ735Updated 3 weeks ago
- Large Context Attentionβ733Updated 7 months ago
- π³ Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"β839Updated 5 months ago
- Ring attention implementation with flash attentionβ853Updated last month
- Pipeline Parallelism for PyTorchβ778Updated last year
- Annotated version of the Mamba paperβ489Updated last year
- [ICLR2025 Spotlightπ₯] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parametersβ571Updated 6 months ago
- Implementation of Rotary Embeddings, from the Roformer paper, in Pytorchβ744Updated last month
- π Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flashβ¦β264Updated last month
- Scalable and Performant Data Loadingβ295Updated last week
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793β435Updated 3 months ago
- LLM KV cache compression made easyβ600Updated this week
- H-Net: Hierarchical Network with Dynamic Chunkingβ690Updated last month
- Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 FP8/NVFP4/MXFP4β902Updated last week
- π Efficient implementations of state-of-the-art linear attention modelsβ3,091Updated this week
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Coresβ330Updated 8 months ago
- Building blocks for foundation models.β541Updated last year
- depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.β721Updated 4 months ago
- Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)β392Updated last week
- β298Updated 4 months ago
- For optimization algorithm research and development.β532Updated this week
- π₯ A minimal training framework for scaling FLA modelsβ233Updated 2 weeks ago
- Microsoft Automatic Mixed Precision Libraryβ618Updated 11 months ago
- A Quirky Assortment of CuTe Kernelsβ435Updated this week
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorchβ359Updated last year
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Ruleβ209Updated 5 months ago