Unofficial Scalable-Softmax Is Superior for Attention
☆21May 30, 2025Updated last year
Alternatives and similar repositories for Scalable-Softmax
Users that are interested in Scalable-Softmax are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Robust Tracking via Mamba-based Context-aware Token Learning (AAAI 2025)☆16Nov 6, 2025Updated 11 months ago
- The official implementation of HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization☆19Mar 7, 2025Updated last year
- Implementations of the XNOR networks☆12Aug 9, 2017Updated 9 years ago
- ☆13Feb 24, 2021Updated 5 years ago
- ☆16May 24, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Revisiting Parameter Sharing for Automatic Neural Channel Number Search, NeurIPS 2020☆21Nov 15, 2020Updated 5 years ago
- ☆13Jul 28, 2025Updated last year
- ☆10Jul 27, 2026Updated 3 months ago
- ☆14Jul 13, 2025Updated last year
- Dynamical low rank training for neural networks☆11Aug 24, 2023Updated 3 years ago
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations☆22Dec 24, 2025Updated 10 months ago
- [ICLR2025] Learning Spatial-Semantic Features for Robust Video Object Segmentation☆16Dec 18, 2025Updated 10 months ago
- ☆19Nov 6, 2023Updated 2 years ago
- 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.
- Official Pytorch implementation of Chromatic Graph Transformers☆10Jun 14, 2023Updated 3 years ago
- Clustered Compositional Embeddings☆13Oct 25, 2023Updated 3 years ago
- ☆13Apr 16, 2024Updated 2 years ago
- 4th place solution to datafactory challenge by Intermarché.☆12Jun 28, 2021Updated 5 years ago
- ☆14Mar 19, 2026Updated 7 months ago
- Code to reproduce key results for "Interpreting Attention Layer Outputs with Sparse Autoencoders"☆11Jul 27, 2024Updated 2 years ago
- torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.☆25Mar 29, 2024Updated 2 years ago
- About Code release for "FlashBias: Fast Computation of Attention with Bias" (NeurIPS 2025), https://arxiv.org/abs/2505.12044☆35Nov 17, 2025Updated 11 months ago
- ✨🌲 Hierarchical extreme multiclass and multi-label classification.☆19Jan 5, 2023Updated 3 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆22Feb 11, 2022Updated 4 years ago
- Ἀνατομή is a PyTorch library to analyze representation of neural networks☆13Jan 31, 2024Updated 2 years ago
- ☆12Jan 17, 2024Updated 2 years ago
- [NeurIPS'25] Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders☆16May 28, 2025Updated last year
- ☆31Aug 11, 2024Updated 2 years ago
- ☆13Sep 16, 2024Updated 2 years ago
- Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops☆30Mar 16, 2024Updated 2 years ago
- Open Set Video HOI detection from Action-centric Chain-of-Look Prompting, ICCV2023☆12Oct 3, 2023Updated 3 years ago
- ☆13May 30, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆17Aug 24, 2026Updated 2 months ago
- iADMM for a low-rank representation optimization problem☆13Feb 5, 2021Updated 5 years ago
- The Hessian of tall-skinny networks is easy to invert☆17Sep 5, 2026Updated last month
- [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Mod…☆31Mar 12, 2024Updated 2 years ago
- ☆25Nov 16, 2025Updated 11 months ago
- ACL 2023☆38Jun 6, 2023Updated 3 years ago
- [Preprint] Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Prunin…☆41Sep 9, 2025Updated last year