pleto's Feed · Scour

CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs

arxiv.org·1d

🧠Large Language Models (LLMs)

Pruning Minimal Reasoning Graphs for Efficient Retrieval-Augmented Generation

arxiv.org·1d

🔍Retrieval-augmented generation

How Painkiller RTX Uses Generative AI to Modernize Game Assets at Scale

developer.nvidia.com·2d

⚙️AI Infrastructure Automation

How to Build a Document Processing Pipeline for RAG with Nemotron

developer.nvidia.com·2d

💬Prompt optimizations for LLM serving

Loading more...