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.
☆28May 3, 2025Updated 10 months ago
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☆18Mar 7, 2025Updated last year
- [ICML 2025] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models☆17Nov 4, 2025Updated 4 months ago
- Don't just regulate gradients like in Muon, regulate the weights too☆32Jul 30, 2025Updated 7 months ago
- ☆12Apr 29, 2024Updated last year
- ☆14Oct 3, 2024Updated last year
- 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.
- ☆136May 29, 2025Updated 9 months ago
- RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment☆16Dec 19, 2024Updated last year
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆23Apr 30, 2025Updated 10 months ago
- ☆21Jan 16, 2025Updated last year
- ☆18Dec 2, 2024Updated last year
- ☆16Sep 17, 2024Updated last year
- [ICLR-2026] Official Implementation of our paper "THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning".☆32Feb 26, 2026Updated 3 weeks ago
- [ICLR 2026] BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs☆17May 21, 2025Updated 10 months ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆101Sep 30, 2024Updated last year
- 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.
- ☆23Mar 7, 2025Updated last year
- Code to train Sentence BERT Japanese model for Hugging Face Model Hub☆11Aug 8, 2021Updated 4 years ago
- ☆15Jul 13, 2025Updated 8 months ago
- MobileLLM-R1☆77Sep 30, 2025Updated 5 months ago
- Clustered Compositional Embeddings☆11Oct 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"☆10Dec 30, 2024Updated last year
- Implementation of Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems☆14Nov 11, 2023Updated 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.
- A Zen approach to configuring your Python project☆16Feb 27, 2026Updated 3 weeks ago
- sigma-MoE layer☆21Jan 5, 2024Updated 2 years ago
- ☆12Sep 16, 2024Updated last year
- Suri: Multi-constraint instruction following for long-form text generation (EMNLP’24)☆27Oct 3, 2025Updated 5 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆50Oct 18, 2024Updated last year
- ☆23Sep 19, 2024Updated last year
- CoV: Chain-of-View Prompting for Spatial Reasoning☆52Jan 23, 2026Updated 2 months ago
- Mixture of Attention Heads☆52Oct 10, 2022Updated 3 years ago
- ☆13Nov 5, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- 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 9 months ago
- ☆29Apr 7, 2024Updated last year
- This is a simple torch implementation of the high performance Multi-Query Attention☆16Aug 23, 2023Updated 2 years ago
- The repository for papaer "Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs"☆14Dec 16, 2024Updated last year
- Official Implementation of FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration☆30Nov 22, 2025Updated 4 months ago
- ☆12Jan 17, 2024Updated 2 years ago