Spotlight Attention: Extreme KV Cache Pruning for Efficient LLM Generation
☆13Jun 2, 2026Updated 5 months ago
Alternatives and similar repositories for spotlight
Users that are interested in spotlight are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Source Code for 'Beginning MATLAB and Simulink' by Sulaymon Eshkabilov☆11Nov 13, 2019Updated 6 years ago
- A Dynamic Stiefel Graph Neural Network for Efficient Spatio-Temporal Time Series Forecasting☆12May 11, 2026Updated 6 months ago
- Official implementation of paper: Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting☆16Feb 20, 2026Updated 8 months ago
- ☆14Nov 18, 2025Updated 11 months ago
- A novel multi-domain fusion network based on sample intercorrelation (SIMFNet) is proposed. The first mulitvariate aquatic human activity…☆30Dec 25, 2023Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- "We have sought for firm ground and found none. The deeper we penetrate, the more restless becomes the universe; all is rushing about and…☆11Dec 19, 2020Updated 5 years ago
- Polyglot skipgram embeddings, and their many health benefits☆12Feb 2, 2020Updated 6 years ago
- Implementation of Paper Generating Sequences With Recurrent Neural Networks☆10Jun 20, 2018Updated 8 years ago
- A blog where I write about research papers and blog posts I read.☆12Nov 20, 2024Updated last year
- This repo provides a couple of easy-to-use template scripts to help you set up a custom jupyter kernel on a AWS Sagemaker Jupyter Noteboo…☆11Jun 17, 2021Updated 5 years ago
- Code for our paper "Localizing Lying in Llama"☆15Apr 24, 2025Updated last year
- Simulator for LLM inference on an abstract 3D AIMC-based accelerator☆36Sep 18, 2025Updated last year
- PRML Page-by-page配套资料，对PRML全书及各章节的review☆18Apr 16, 2024Updated 2 years ago
- ☆13Jun 25, 2021Updated 5 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Webcrawler to collect cookie data and usage purposes, built using OpenWPM.☆13Jun 3, 2023Updated 3 years ago
- Code to reproduce paper "Exploring Longitudinal Effects of Session-based Recommendations" in RecSys 2020☆15Nov 21, 2022Updated 3 years ago
- FPGA-based SNN Accelerator Toy☆51Apr 17, 2026Updated 6 months ago
- 🏆1st place in the MICCAI challenge CrossMoDA 2023☆19Sep 5, 2025Updated last year
- ☆12Jul 11, 2021Updated 5 years ago
- Github repository for CLAPACK (fork of CLAPACK 3.2.1 patched for our needs)☆10Aug 15, 2018Updated 8 years ago
- Code for "HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking"☆108Nov 18, 2025Updated 11 months ago
- Please visit https://github.com/HKUSTDial/NL2SQL360 to get the official code!☆10Sep 1, 2024Updated 2 years ago
- ☆20Sep 10, 2020Updated 6 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Convert lecture videos to slides in one line. Takes an input of a directory containing your lecture videos and outputs a directory contai…☆13Oct 17, 2021Updated 5 years ago
- 用pytorch训练ssd，相比原版pytorch-ssd改动了不少☆11Jul 4, 2022Updated 4 years ago
- homework in SCUT_SE☆12Nov 9, 2021Updated 5 years ago
- [CVPR2026] V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs☆24Dec 8, 2025Updated 11 months ago
- Repository for SAiDL Spring 2022 Induction Assignment☆11Feb 10, 2022Updated 4 years ago
- HiAE - A High-Throughput Authenticated Encryption Algorithm for Cross-Platform Efficiency.☆19May 27, 2026Updated 5 months ago
- In-Session Personalization Workshop for eCommerce, April 2021, and the MICES Workshop in June 2021.☆24Jun 29, 2021Updated 5 years ago
- Official Repo of "CIBench: Evaluation of LLMs as Code Interpreter "☆15Jul 19, 2024Updated 2 years ago
- GBDT-based model with efficient unlearning (SIGMOD 2023)☆10Sep 7, 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.
- 投资组合评比器，基于python3.8和mysql8.0。由Concyclics和wingholy完成主要编程工作，可实现对于蛋卷基金和且慢基金平台投资组合信息的收集和对比。☆11Jun 18, 2021Updated 5 years ago
- Experiments with Langchain using different approaches on Google colab☆25Mar 29, 2024Updated 2 years ago
- Interpreting Chest X-rays Like a Radiologist: A Benchmark with Clinical Reasoning, release the dataset and the model weight☆12May 26, 2025Updated last year
- B站爬虫☆15Dec 10, 2023Updated 2 years ago
- ☆12Oct 15, 2025Updated last year
- Data Layers for Caffe☆13Apr 15, 2016Updated 10 years ago
- MiniMax AI 驱动的狼人杀游戏框架☆10Dec 2, 2025Updated 11 months ago
Are these results useful?