The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
☆92Jul 17, 2025Updated 11 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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Efficient Transformers with Dynamic Token Pooling☆68May 20, 2023Updated 3 years ago
- The evaluation framework for training-free sparse attention in LLMs☆125Jan 27, 2026Updated 5 months ago
- ☆11Oct 11, 2023Updated 2 years ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆37Aug 14, 2024Updated last year
- ☆15Jun 4, 2024Updated 2 years ago
- 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.
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆24Aug 18, 2024Updated last year
- Language models scale reliably with over-training and on downstream tasks☆102Apr 2, 2024Updated 2 years ago
- Official Implementation of APB (ACL 2025 main Oral) and Spava (ACL 2026 main).☆37Apr 6, 2026Updated 3 months ago
- ☆44Oct 11, 2025Updated 8 months ago
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆18Mar 15, 2024Updated 2 years ago
- ☆20May 30, 2024Updated 2 years ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆133Jun 24, 2025Updated last year
- The code for creating the iGSM datasets in papers "Physics of Language Models Part 2.1, Grade-School Math and the Hidden Reasoning Proces…☆88Jan 12, 2025Updated last year
- Source-to-Source Debuggable Derivatives in Pure Python☆15Jan 23, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆539Feb 10, 2025Updated last year
- Awesome Triton Resources☆43Apr 27, 2025Updated last year
- [EMNLP 2023] Official implementation of the algorithm ETSC: Exact Toeplitz-to-SSM Conversion our EMNLP 2023 paper - Accelerating Toeplitz…☆14Oct 17, 2023Updated 2 years ago
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- ☆17Dec 19, 2024Updated last year
- ☆19Jan 27, 2025Updated last year
- Implement some method of LLM KV Cache Sparsity☆41Jun 6, 2024Updated 2 years ago
- Efficient PScan implementation in PyTorch☆17Jan 2, 2024Updated 2 years ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆396Jul 10, 2025Updated 11 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Compression for Foundation Models☆36Jul 21, 2025Updated 11 months ago
- train with kittens!☆66Oct 25, 2024Updated last year
- Transformers components but in Triton☆34May 9, 2025Updated last year
- A single-file educational implementation for understanding vLLM's core concepts and running LLM inference.☆45Apr 7, 2026Updated 3 months ago
- Algorithms for approximate attention in LLMs☆22Apr 14, 2025Updated last year
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆40Dec 2, 2023Updated 2 years ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆43Dec 29, 2025Updated 6 months ago
- Checkpointable dataset utilities for foundation model training☆32Jan 29, 2024Updated 2 years ago
- RADLADS training code☆44May 7, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆83Apr 16, 2024Updated 2 years ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆25Jun 6, 2024Updated 2 years ago
- continous batching and parallel acceleration for RWKV6☆22Jun 28, 2024Updated 2 years ago
- A basic pure pytorch implementation of flash attention☆17Oct 28, 2024Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆169Oct 13, 2025Updated 8 months ago
- A High-Throughput Multi-GPU System for Graph-Based Approximate Nearest Neighbor Search☆21Jul 22, 2025Updated 11 months ago
- [AAAI26] LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs☆55Dec 7, 2025Updated 7 months ago