ahennequ / pytorch-custom-mmaView external linksLinks
☆29Oct 3, 2022Updated 3 years ago
Alternatives and similar repositories for pytorch-custom-mma
Users that are interested in pytorch-custom-mma are comparing it to the libraries listed below
Sorting:
- Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆29Sep 12, 2025Updated 5 months ago
- Curse-of-memory phenomenon of RNNs in sequence modelling☆19May 8, 2025Updated 9 months ago
- Official Repository for Efficient Linear-Time Attention Transformers.☆18Jun 2, 2024Updated last year
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆220Feb 13, 2023Updated 3 years ago
- ☆12Jan 29, 2021Updated 5 years ago
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Aug 12, 2023Updated 2 years ago
- Manipulate tensors with PackedSequence and CattedSequence☆12Jan 4, 2026Updated last month
- Advanced Formal Language Theory (263-5352-00L; Frühjahr 2023)☆10Feb 21, 2023Updated 2 years ago
- PyTorch implementation for PaLM: A Hybrid Parser and Language Model.☆10Jan 7, 2020Updated 6 years ago
- Official Implementation of ACL2023: Don't Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span …☆14Aug 25, 2023Updated 2 years ago
- Triton Implementation of HyperAttention Algorithm☆48Dec 11, 2023Updated 2 years ago
- Official code for UnICORNN (ICML 2021)☆28Oct 1, 2021Updated 4 years ago
- ☆33Oct 4, 2024Updated last year
- Depth-Bounded PCFG Induction☆13Apr 19, 2019Updated 6 years ago
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆18Mar 15, 2024Updated last year
- ☆12Sep 1, 2023Updated 2 years ago
- Official repository for the paper "Exploring the Promise and Limits of Real-Time Recurrent Learning" (ICLR 2024)☆13Jun 11, 2025Updated 8 months ago
- Experiments with self-supervised learning☆11Mar 9, 2020Updated 5 years ago
- ☆12Mar 7, 2022Updated 3 years ago
- Code for the paper: Comparing and Contrasting Deep Learning Weather Prediction Backbones on Navier-Stokes and Atmospheric Dynamics☆13Aug 9, 2024Updated last year
- ☆32Jan 7, 2024Updated 2 years ago
- FlexAttention w/ FlashAttention3 Support☆27Oct 5, 2024Updated last year
- Code for "Theoretical Foundations of Deep Selective State-Space Models" (NeurIPS 2024)☆15Jan 7, 2025Updated last year
- ☆35Apr 12, 2024Updated last year
- Variable-order CRFs with structure learning☆17Aug 1, 2024Updated last year
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- ☆16Dec 19, 2024Updated last year
- Legendre decomposition for tensors☆13Oct 29, 2018Updated 7 years ago
- Parallel Associative Scan for Language Models☆18Jan 8, 2024Updated 2 years ago
- 方便扩展的Cuda算子理解和优化框架，仅用在学习使用☆18Jun 13, 2024Updated last year
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆16Aug 3, 2021Updated 4 years ago
- ☆14May 21, 2024Updated last year
- [NeurIPS 2022]MorphTE: Injecting Morphology in Tensorized Embeddings☆17Oct 29, 2022Updated 3 years ago
- Explorations into the recently proposed Taylor Series Linear Attention☆100Aug 18, 2024Updated last year
- ☆20May 30, 2024Updated last year
- Blog post☆17Feb 16, 2024Updated 2 years ago
- ☆18Oct 3, 2022Updated 3 years ago
- Pytorch implementation of Planar Flow☆17Dec 2, 2019Updated 6 years ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73May 26, 2024Updated last year