User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice routing providing a content-based sparse attention mechanism.
☆29May 3, 2025Updated last year
Alternatives and similar repositories for MoSA
Users that are interested in MoSA 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 official implementation of HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization☆19Mar 7, 2025Updated last year
- [ICML 2025] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models☆18Nov 4, 2025Updated 6 months ago
- ☆12Apr 29, 2024Updated 2 years ago
- ☆14Oct 3, 2024Updated last year
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆17Dec 19, 2024Updated last year
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆24May 21, 2025Updated last year
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆24Apr 30, 2025Updated last year
- ☆18Dec 2, 2024Updated last year
- ☆16May 18, 2026Updated last week
- [ICLR-2026] Official Implementation of our paper "THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning".☆32Feb 26, 2026Updated 2 months ago
- ☆19Jan 10, 2025Updated last year
- ☆12Aug 13, 2024Updated last year
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆101Sep 30, 2024Updated last year
- ☆23Mar 7, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆14Jul 13, 2025Updated 10 months ago
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆48Sep 2, 2025Updated 8 months ago
- A summarizer for Japanese articles (but ChatGPT is better)☆10Aug 1, 2022Updated 3 years ago
- Official Pytorch implementation of Chromatic Graph Transformers☆10Jun 14, 2023Updated 2 years ago
- Clustered Compositional Embeddings☆13Oct 25, 2023Updated 2 years ago
- Ἀνατομή is a PyTorch library to analyze representation of neural networks☆13Jan 31, 2024Updated 2 years ago
- [NeurIPS 2024] | An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding☆22Oct 10, 2024Updated last year
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- [ICML 2024] SIRFShampoo: Structured inverse- and root-free Shampoo in PyTorch (https://arxiv.org/abs/2402.03496)☆15Nov 4, 2024Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Implementation of Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems☆15Nov 11, 2023Updated 2 years ago
- [ICLR 2026] BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs☆18May 21, 2025Updated last year
- A Zen approach to configuring your Python project☆17Feb 27, 2026Updated 2 months ago
- ☆12Sep 16, 2024Updated last year
- ☆35Oct 4, 2025Updated 7 months ago
- Suri: Multi-constraint instruction following for long-form text generation [EMNLP’24]☆27Oct 3, 2025Updated 7 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆51Oct 18, 2024Updated last year
- ☆23Sep 19, 2024Updated last year
- Python script to transform the Mobile Detect JSON database into an UA-based mobile detection VCL subroutine easily integrable in any Varn…☆14Nov 13, 2023Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Codes for our paper "AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems"☆13Dec 13, 2024Updated last year
- Unofficial Scalable-Softmax Is Superior for Attention☆20May 30, 2025Updated 11 months ago
- ☆29Apr 7, 2024Updated 2 years ago
- This is a simple torch implementation of the high performance Multi-Query Attention☆16Aug 23, 2023Updated 2 years ago
- ☆12Jan 17, 2024Updated 2 years ago
- [ACL 2026 Findings] CoV: Chain-of-View Prompting for Spatial Reasoning☆60Apr 7, 2026Updated last month
- [ACL Findings 2026] Official Implementation of "FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acc…☆32Apr 14, 2026Updated last month