PiotrNawrot / nano-sparse-attentionLinks
The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
☆92Updated 3 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☆102Updated last month
- Fast and memory-efficient exact attention☆74Updated 8 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
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆147Updated last year
- ☆83Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆206Updated 4 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆156Updated 7 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 11 months ago
- ☆149Updated 2 years ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- ☆130Updated 5 months ago
- ☆121Updated last year
- ☆147Updated 8 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆248Updated last month
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated last year
- Code for studying the super weight in LLM☆119Updated 11 months ago
- Muon fsdp 2☆44Updated 3 months ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆70Updated last year
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆85Updated last year
- Understand and test language model architectures on synthetic tasks.☆237Updated last month
- Language models scale reliably with over-training and on downstream tasks☆100Updated last year
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆241Updated 5 months ago
- ☆96Updated 8 months ago
- ☆52Updated last year
- Stick-breaking attention☆61Updated 4 months ago
- ☆53Updated last year
- ☆55Updated 5 months ago
- Token Omission Via Attention☆127Updated last year