leloykun / flash-attention-minimalLinks
Flash Attention in 300-500 lines of CUDA/C++
☆24Updated last month
Alternatives and similar repositories for flash-attention-minimal
Users that are interested in flash-attention-minimal are comparing it to the libraries listed below
Sorting:
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆89Updated 2 months ago
- Collection of kernels written in Triton language☆155Updated 5 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated 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
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- ☆142Updated 7 months ago
- Fast and memory-efficient exact attention☆69Updated 6 months ago
- ☆126Updated 3 months ago
- A bunch of kernels that might make stuff slower 😉☆59Updated this week
- Triton-based implementation of Sparse Mixture of Experts.☆240Updated last month
- ☆237Updated last week
- ☆112Updated last year
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆140Updated 7 months ago
- Cataloging released Triton kernels.☆260Updated 2 weeks ago
- The evaluation framework for training-free sparse attention in LLMs☆96Updated 3 months ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆94Updated last year
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…☆22Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆186Updated 3 months ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆84Updated 7 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆233Updated 3 weeks ago
- PyTorch bindings for CUTLASS grouped GEMM.☆121Updated 3 months ago
- Code for studying the super weight in LLM☆119Updated 9 months ago
- A minimal implementation of vllm.☆58Updated last year
- a minimal cache manager for PagedAttention, on top of llama3.☆122Updated last year
- ring-attention experiments☆152Updated 11 months ago
- ☆90Updated 10 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆234Updated 10 months ago
- Personal solutions to the Triton Puzzles☆20Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆47Updated last month
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆212Updated last week