PiotrNawrot / nano-sparse-attentionLinks
The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
☆90Updated 5 months ago
Alternatives and similar repositories for nano-sparse-attention
Users that are interested in nano-sparse-attention are comparing it to the libraries listed below
Sorting:
- The evaluation framework for training-free sparse attention in LLMs☆108Updated 3 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- Fast and memory-efficient exact attention☆74Updated 10 months ago
- ☆83Updated 2 years ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆79Updated 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
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆157Updated 9 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆131Updated last year
- ☆124Updated last year
- Code for studying the super weight in LLM☆120Updated last year
- ☆133Updated 7 months ago
- ☆150Updated 2 years ago
- ☆156Updated 10 months ago
- ☆53Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆259Updated 3 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆225Updated 6 months ago
- ☆103Updated 10 months ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications☆52Updated 2 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆244Updated 7 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆87Updated last year
- Cascade Speculative Drafting☆32Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆136Updated last year
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆75Updated last year
- Experiments on Multi-Head Latent Attention☆99Updated last year
- ☆85Updated 2 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆52Updated last year
- ☆61Updated 7 months ago
- Understand and test language model architectures on synthetic tasks.☆248Updated 3 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆90Updated last year