Flash Attention implementation that returns both output and attention scores. High-performance, memory-efficient attention with score extraction for analysis and visualization.
☆16Feb 6, 2026Updated 7 months ago
Alternatives and similar repositories for Flash_Attn_with_Score
Users that are interested in Flash_Attn_with_Score are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [CVPR2025] FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression☆62Oct 10, 2025Updated 11 months ago
- ☆70Jan 23, 2026Updated 8 months ago
- ContextOS: AI-Centric Proactive Agent Framework☆20Nov 18, 2025Updated 10 months ago
- [CVPR2026 Highlight] FlexMem: Scaling the Long Video Understanding of MLLMs via Visual Memory Mechanism☆41Apr 10, 2026Updated 5 months ago
- ☆27Jan 30, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Project for Dynamic Capsule Attention☆12Dec 7, 2019Updated 6 years ago
- XNAS: An effective, modular, and flexible Neural Architecture Search (NAS) framework.☆47Jun 29, 2022Updated 4 years ago
- ☆10Jul 30, 2021Updated 5 years ago
- ☆18Nov 15, 2024Updated last year
- [AAAI26] Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment☆22Dec 30, 2025Updated 8 months ago
- ☆13Jun 20, 2022Updated 4 years ago
- ☆19Jan 7, 2026Updated 8 months ago
- Official Code for "Knowing what it is: Semantic-enhanced Dual Attention Transformer" (TMM2022)☆19Oct 15, 2022Updated 3 years ago
- 🚀 Official code for “XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression”, …☆48Jan 27, 2026Updated 7 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- The official implement of "Routing Experts: Learning to Route Dynamic Experts in Existing Multi-modal Large Language Models"☆17Mar 24, 2025Updated last year
- [AAAI2023] Repo for the paper ''End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation''.☆23Apr 1, 2023Updated 3 years ago
- The official implement of "Grounded Chain-of-Thought for Multimodal Large Language Models"☆27Jul 21, 2025Updated last year
- [EMNLP 2022] D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat☆33Oct 28, 2022Updated 3 years ago
- ☆25Dec 11, 2021Updated 4 years ago
- Code release for AccDiffusionV2 (TPAMI)☆33Nov 4, 2025Updated 10 months ago
- ☆35Jul 4, 2024Updated 2 years ago
- ☆90May 10, 2024Updated 2 years ago
- Official Pytorch implementation of Super Vision Transformer (IJCV)☆43Aug 3, 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.
- Visual Instruction Tuning for Qwen2 Base Model☆43Jun 29, 2024Updated 2 years ago
- 共产中文报告生成器，用于生成有伏特加味的参水报告☆38Mar 2, 2022Updated 4 years ago
- 【NeurIPS 2024】Dense Connector for MLLMs☆183Oct 14, 2024Updated last year
- Pytorch implementation of our paper accepted by TPAMI 2023 — Lottery Jackpots Exist in Pre-trained Models☆35Jun 19, 2023Updated 3 years ago
- Dynamic Distribution Pruning for Efficient Network Architecture Search☆48Jun 24, 2019Updated 7 years ago
- Pytorch implementation of our paper accepted by IEEE TNNLS, 2021 -- Filter Sketch for Network Pruning☆53Feb 11, 2021Updated 5 years ago
- [ICLR2025] LLaVA-HR: High-Resolution Large Language-Vision Assistant☆248Aug 14, 2024Updated 2 years ago
- The official implementation for Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification (CVPR21)☆69Nov 15, 2022Updated 3 years ago
- ☆55Jun 3, 2026Updated 3 months 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.
- 自我量化指南☆43Sep 11, 2026Updated last week
- [NeurIPS 2025 Spotlight] Official PyTorch implementation of Vgent☆51Nov 30, 2025Updated 9 months ago
- LUCY: Linguistic Understanding and Control Yielding Early Stage of Her☆61Apr 14, 2025Updated last year
- The official code for Relational Context Learning for Human-Object Interaction Detection, CVPR2023.☆55Apr 23, 2023Updated 3 years ago
- ☆55Jul 30, 2024Updated 2 years ago
- [CVPR 2026 Findings] Eevee: Towards Close-up High-resolution Video-based Virtual Try-on☆79Sep 4, 2026Updated 2 weeks ago
- Official code repo for our work "Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models"☆54Jun 17, 2025Updated last year