epfml / dynamic-sparse-flash-attentionLinks
☆149Updated 2 years ago
Alternatives and similar repositories for dynamic-sparse-flash-attention
Users that are interested in dynamic-sparse-flash-attention are comparing it to the libraries listed below
Sorting:
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆240Updated 3 months ago
- ☆122Updated last year
- Fast and memory-efficient exact attention☆70Updated 7 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆241Updated last month
- Some preliminary explorations of Mamba's context scaling.☆217Updated last year
- Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"☆120Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆89Updated 2 months ago
- ☆83Updated last year
- Triton implementation of FlashAttention2 that adds Custom Masks.☆135Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆216Updated last year
- Understand and test language model architectures on synthetic tasks.☆229Updated last week
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆94Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- Low-bit optimizers for PyTorch☆131Updated last year
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆189Updated 3 months ago
- This repository contains the experimental PyTorch native float8 training UX☆224Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆129Updated 9 months ago
- ☆112Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 10 months ago
- ☆156Updated 2 years ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆70Updated last year
- A toolkit for scaling law research ⚖☆52Updated 8 months ago
- 🔥 A minimal training framework for scaling FLA models☆255Updated 3 weeks ago
- Explorations into some recent techniques surrounding speculative decoding☆286Updated 9 months ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆79Updated last year
- ☆126Updated 4 months ago
- JAX bindings for Flash Attention v2☆92Updated 3 weeks ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆96Updated 2 years ago
- ☆218Updated 2 years ago