Transformer Optimization — 3 Technical Articles

Oct 14, 2025 · Artificial Intelligence

How DeepSeek’s Lightning Indexer Enables Efficient Sparse Attention for Long Texts

The article explains how DeepSeek’s Lightning Indexer acts as a memory‑filtering expert that computes index scores, selects the top‑k relevant tokens, and maps a compact formula to FP8 kernel code, reducing attention complexity from 128K to 2048 tokens for massive sequences.

DeepSeekFP8Lightning Indexer

0 likes · 7 min read

How DeepSeek’s Lightning Indexer Enables Efficient Sparse Attention for Long Texts

AI Frontier Lectures

Jul 17, 2025 · Artificial Intelligence

How Skip-Vision Cuts Multimodal Model Costs by Up to 75% Without Losing Accuracy

Skip-Vision introduces a token‑skipping framework for vision‑language models that dramatically reduces training and inference FLOPs—saving 22%‑40% training time and 40%‑75% inference cost—while preserving performance on benchmarks such as MMBench, MMVet, and MMStar.

Multimodal EfficiencySkip-VisionToken Skipping

0 likes · 8 min read

How Skip-Vision Cuts Multimodal Model Costs by Up to 75% Without Losing Accuracy

Ops Development & AI Practice

Apr 2, 2025 · Artificial Intelligence

How Cache‑Augmented Generation (CAG) Supercharges LLM Inference

Cache‑Augmented Generation (CAG) speeds up large language model text generation by caching the Transformer attention layer’s key‑value states, dramatically reducing the quadratic compute cost of autoregressive decoding while keeping the model’s knowledge unchanged.

AI performanceCAGCache‑augmented generation

0 likes · 9 min read

How Cache‑Augmented Generation (CAG) Supercharges LLM Inference