MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention (NeurIPS'25 Spotlight)
☆27Feb 22, 2026Updated 6 months ago
Alternatives and similar repositories for monarch-attention
Users that are interested in monarch-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:
- Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation (ICML'24 Oral)☆13Jul 22, 2024Updated 2 years ago
- [EMNLP 2024] Quantize LLM to extremely low-bit, and finetune the quantized LLMs☆17Jul 18, 2024Updated 2 years ago
- ☆14Jul 13, 2025Updated last year
- Clustered Compositional Embeddings☆13Oct 25, 2023Updated 2 years ago
- ☆17Jul 25, 2023Updated 3 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.
- [ICML 2021] "Double-Win Quant: Aggressively Winning Robustness of Quantized DeepNeural Networks via Random Precision Training and Inferen…☆16Feb 13, 2022Updated 4 years ago
- Implementation and evaluation of Scaling Embedding Layers in Language Models research paper☆17Feb 2, 2026Updated 7 months ago
- ☆13Jul 2, 2025Updated last year
- Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent☆16Sep 8, 2022Updated 4 years ago
- Experiments on the impact of depth in transformers and SSMs.☆47Oct 23, 2025Updated 10 months ago
- Continual Memorization of Factoids in Large Language Models☆12Nov 20, 2024Updated last year
- [ICLR 2025] Official implementation of paper "Dynamic Low-Rank Sparse Adaptation for Large Language Models".☆25Mar 16, 2025Updated last year
- ☆54May 20, 2024Updated 2 years ago
- Code for "LLM Embeddings Improve Test-time Adaptation to Tabular Y|X-Shifts"☆12Oct 17, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Efficient kernel for RMS normalization with fused operations, includes both forward and backward passes, compatibility with PyTorch.☆13Jun 5, 2024Updated 2 years ago
- Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.☆17Apr 25, 2021Updated 5 years ago
- ☆16Nov 4, 2021Updated 4 years ago
- ☆13Aug 14, 2022Updated 4 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- Official Pytorch implementation of Chromatic Graph Transformers☆10Jun 14, 2023Updated 3 years ago
- Ἀνατομή is a PyTorch library to analyze representation of neural networks☆13Jan 31, 2024Updated 2 years ago
- Confident Adaptive Transformers☆15Apr 18, 2021Updated 5 years ago
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 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.
- [ICLR2026] The open-source code for FlowCache, including accelerated implementations of the MAGI-1 and Skyreels-V2.☆34Apr 24, 2026Updated 4 months ago
- Code for the EMNLP24 paper "A simple and effective L2 norm based method for KV Cache compression."☆19Dec 13, 2024Updated last year
- ☆12Sep 16, 2024Updated 2 years ago
- Code for EMNLP 2023 paper: DALE: Generative Data Augmentation for Low-Resource Legal NLP☆11Oct 27, 2023Updated 2 years ago
- Code as World: Agentic Discovery of Executable World Representations for Physical Reasoning☆452Aug 31, 2026Updated 2 weeks ago
- ☆36Apr 12, 2024Updated 2 years ago
- ☆33Nov 11, 2024Updated last year
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆36Sep 12, 2025Updated last year
- Explaining neural decisions contrastively to alternative decisions.☆24Mar 18, 2021Updated 5 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆36Oct 3, 2023Updated 2 years ago
- Official Code Repository for the paper "Key-value memory in the brain"☆34Feb 25, 2025Updated last year
- iADMM for a low-rank representation optimization problem☆13Feb 5, 2021Updated 5 years ago
- Offical implementation of "MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map" (NeurIPS2024 Oral)☆36Jan 18, 2025Updated last year
- QuIP quantization☆66Mar 17, 2024Updated 2 years ago
- Official implementation of RMoE (Layerwise Recurrent Router for Mixture-of-Experts)☆33Aug 4, 2024Updated 2 years ago
- Code for experiments on transformers using Markovian data.☆22Nov 22, 2024Updated last year