Kwai Summary Attention
☆57May 8, 2026Updated 2 months ago
Alternatives and similar repositories for KSA
Users that are interested in KSA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆47Nov 19, 2025Updated 7 months ago
- The official implementation of Recurrent Diffusion for Large-Scale Parameter Generation.☆81Sep 24, 2025Updated 9 months ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Give us minutes, we give back a faster Mamba. The official implementation of "Faster Vision Mamba is Rebuilt in Minutes via Merged Token …☆39Dec 18, 2024Updated last year
- continous batching and parallel acceleration for RWKV6☆23Jun 28, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Official codes for COLING 2024 paper "Robust and Scalable Model Editing for Large Language Models": https://arxiv.org/abs/2403.17431v1☆14Mar 27, 2024Updated 2 years ago
- [ICCV 2025] EA-ViT: Efficient Adaptation for Elastic Vision Transformer☆27Jul 28, 2025Updated 11 months ago
- ☆17Dec 19, 2024Updated last year
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆150Feb 25, 2026Updated 4 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆52Jul 4, 2025Updated last year
- Muon in Int8 Precision Made Possible☆20Jun 18, 2026Updated 3 weeks ago
- Official Project Page for HLA: Higher-order Linear Attention (https://arxiv.org/abs/2510.27258)☆102Jun 15, 2026Updated 3 weeks ago
- A Triton-only attention backend for vLLM☆27Mar 17, 2026Updated 3 months ago
- ☆40Dec 14, 2025Updated 7 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Cute layout visualization☆42Jan 18, 2026Updated 5 months ago
- A method for evaluating the high-level coherence of machine-generated texts. Identifies high-level coherence issues in transformer-based …☆12Mar 18, 2023Updated 3 years ago
- ☆47Jun 16, 2025Updated last year
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated last year
- PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing☆21Mar 18, 2025Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated 11 months ago
- High-performance LLM operator library built on TileLang.☆159Updated this week
- Compositional Muon release☆23Jun 5, 2026Updated last month
- [ACL 2025] iAgent: LLM Agent as a Shield between User and Recommender Systems☆33May 23, 2025Updated last year
- 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.
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆92Jul 17, 2025Updated 11 months ago
- FlashMemory DS-V4 Retriever: a lightweight retriever that sparsifies DeepSeek-V4 CSA KV-cache. Weights available on Hugging Face.☆89Updated this week
- Official Codebase: LT2: Linear-Time Looped Transformers.☆49May 27, 2026Updated last month
- 🔥 [ICML'26] ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs☆29Jun 29, 2026Updated 2 weeks ago
- Official code for HiLS-Attention☆94Updated this week
- Rethinking the Trust Region in LLM Reinforcement Learning☆61Mar 2, 2026Updated 4 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆173Feb 27, 2026Updated 4 months ago
- ☆62Jun 17, 2024Updated 2 years ago
- Transformers components but in Triton☆34May 9, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Debug print operator for cudagraph debugging☆18Aug 2, 2024Updated last year
- FlashKDA: high-performance Kimi Delta Attention kernels☆450May 26, 2026Updated last month
- ☆20Aug 14, 2025Updated 11 months ago
- Official code for the NeurIPS25 paper "RAT: Bridging RNN Efficiencyand Attention Accuracy in Language Modeling" (https://arxiv.org/abs/25…☆26Dec 10, 2025Updated 7 months ago
- Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity (ACL 2025, oral)☆35Jun 14, 2025Updated last year
- ☆375Jun 15, 2026Updated 3 weeks ago
- ☆113May 31, 2025Updated last year