# IndexCache **Source:** https://www.startuphub.ai/startups/indexcache **Profile type:** Startup > Optimizing LLM inference for faster and cheaper long-context processing. ## About IndexCache is a novel technique developed by researchers at Tsinghua University and Z.ai that significantly reduces computational redundancy in sparse attention models. This leads to faster inference times and lower costs for large language models, especially those with long context windows. ## Key facts - **Slug:** indexcache - **Website:** https://forsale.dynadot.com - **Location:** Beijing, China - **Founded:** 2023-01-01 - **Operating status:** Active - **Sectors / tags:** Artificial Intelligence, Machine Learning, AI Infrastructure, Foundation Model, Large Language Model, Transformer Architecture, Sparse Attention, Inference Optimization, Generative AI - **Social:** - GitHub: https://github.com/Tsinghua-IA-Group/IndexCache ## Frequently asked ### What does IndexCache do? IndexCache is a novel technique developed by researchers at Tsinghua University and Z.ai that significantly reduces computational redundancy in sparse attention models. This leads to faster inference times and lower costs for large language models, especially those with long context windows. ### Where is IndexCache headquartered? IndexCache is headquartered in Beijing, China. ### When was IndexCache founded? IndexCache was founded in 2023. ### What industry does IndexCache operate in? IndexCache operates in Artificial Intelligence, Machine Learning, AI Infrastructure, Foundation Model, Large Language Model, Transformer Architecture. ## JSON-LD Structured data aligned with this page's `