The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
☆93Jul 17, 2025Updated last year
Alternatives and similar repositories for nano-sparse-attention
Users that are interested in nano-sparse-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The evaluation framework for training-free sparse attention in LLMs☆134Jan 27, 2026Updated 9 months ago
- Efficient Transformers with Dynamic Token Pooling☆67May 20, 2023Updated 3 years ago
- ptdeco is a library for model optimization by matrix decomposition built on top of PyTorch☆10May 7, 2025Updated last year
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆36Aug 14, 2024Updated 2 years ago
- Language models scale reliably with over-training and on downstream tasks☆104Apr 2, 2024Updated 2 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆19Mar 15, 2024Updated 2 years ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆135Jun 24, 2025Updated last year
- Official Implementation of APB (ACL 2025 main Oral) and Spava (ACL 2026 main).☆37Apr 6, 2026Updated 7 months ago
- ☆16Jun 4, 2024Updated 2 years ago
- [ICML 2026] Sparser Block-Sparse Attention via Token Permutation☆33May 22, 2026Updated 5 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆172Oct 13, 2025Updated last year
- continous batching and parallel acceleration for RWKV6☆23Jun 28, 2024Updated 2 years ago
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆24Aug 18, 2024Updated 2 years ago
- Code and data to explore neural scaling laws of xLSTM and Transformer models.☆24Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Training hybrid models for dummies.☆30Nov 1, 2025Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆545Feb 10, 2025Updated last year
- Sparsity as a Variance Regulator for Improved Depth Utilization in Language Models☆16May 11, 2026Updated 5 months ago
- PyTorch implementation of the Flash Spectral Transform Unit.☆23Sep 19, 2024Updated 2 years ago
- ☆125May 19, 2025Updated last year
- Dependency Parsing as Sequence Labeling with Python3+ and PyTorch1+ and MTL☆10Nov 21, 2019Updated 6 years ago
- TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning☆21Oct 10, 2026Updated 3 weeks ago
- Simple & Scalable Pretraining for Neural Architecture Research☆349Mar 31, 2026Updated 7 months ago
- ☆13Apr 15, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆14Nov 20, 2022Updated 3 years ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Jan 23, 2024Updated 2 years ago
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆14Apr 17, 2025Updated last year
- Efficient PScan implementation in PyTorch☆17Jan 2, 2024Updated 2 years ago
- ☆139May 29, 2025Updated last year
- Implement Flash Attention using Cute.☆113Dec 17, 2024Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆288Jul 6, 2025Updated last year
- ☆28Feb 26, 2026Updated 8 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆414Jul 10, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Implement some method of LLM KV Cache Sparsity☆41Jun 6, 2024Updated 2 years ago
- Triton-based implementation of Sparse Mixture of Experts.☆281Oct 3, 2025Updated last year
- "R1-Ranker: Teaching LLM Rankers to Reason", Tao Feng, Zhigang Hua, Zijie Lei, Yan Xie, Shuang Yang, Bo Long, Jiaxuan You☆14Feb 5, 2026Updated 9 months ago
- This is the official code for OThink-R1 project.☆21Jun 19, 2025Updated last year
- A basic pure pytorch implementation of flash attention☆17Oct 28, 2024Updated 2 years ago
- Experiments on the impact of depth in transformers and SSMs.☆48Oct 23, 2025Updated last year
- AI-powered, local-first Todoist analytics, automations, and dashboard with summaries and chat over cached activity.☆33Aug 31, 2026Updated 2 months ago