PiotrNawrot / nano-sparse-attentionLinks
The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
☆84Updated last month
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 source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆61Updated 10 months ago
- ☆81Updated last year
- The evaluation framework for training-free sparse attention in LLMs☆90Updated 2 months ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆81Updated 9 months ago
- Fast and memory-efficient exact attention☆70Updated 5 months ago
- Code for studying the super weight in LLM☆115Updated 8 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆151Updated 4 months ago
- ☆118Updated last year
- Using FlexAttention to compute attention with different masking patterns☆44Updated 11 months ago
- ☆53Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆128Updated 8 months ago
- ☆85Updated last year
- ☆148Updated 2 years ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆141Updated last year
- [NeurIPS 2024] Low rank memory efficient optimizer without SVD☆30Updated last month
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆70Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆160Updated 2 months ago
- From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…☆47Updated 4 months ago
- ☆80Updated 5 months ago
- Understand and test language model architectures on synthetic tasks.☆221Updated last month
- ☆85Updated 7 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆240Updated 2 months ago
- Stick-breaking attention☆59Updated last month
- ☆68Updated last year
- Language models scale reliably with over-training and on downstream tasks☆98Updated last year
- ☆127Updated last year
- ☆51Updated 2 months ago
- ☆51Updated 9 months ago
- Load compute kernels from the Hub☆244Updated this week