Ling HuangLarge Language Models — Retrieval Augmented Generation (RAG), Part 612 RAG Pain Points and Proposed Solutions to the core challenges of RAG2d ago2d ago
Ling HuangLarge Language Model — LLM Model Efficient InferenceA Survey on Efficient Inference for Large Language Models2d ago2d ago
Ling HuangLarge Language Model — LLM Model InfraMainstream LLM architecture Common architecture types:Jul 2Jul 2
Ling HuangLarge Language Model — LLM Agents, Part 4An AI Agent is a piece of software that performs tasks on behalf of a user. They can automate processes, make decisions, and interact…Jun 30Jun 30
Ling HuangLarge Language Models —Fine TuningTen Commandments to Deploy Fine-Tuned Models in ProdJun 28Jun 28
Ling HuangLarge Language Models — Retrieval Augmented Generation (RAG), Part 5Intro of EmbeddingJun 19Jun 19
Ling HuangFP8 from NVIDIAIn order to better understand FP8, this article will focus on four issues and goals to explain to you:Jun 19Jun 19
Ling HuangLarge Language Models — Retrieval Augmented Generation (RAG), Part 4RAG DecompositionJun 12Jun 12
Ling HuangRecommendation System Using LLM, Part 6Large model here refers to a computationally intensive large model similar to the Transformer structure based on attention. Because if we…Jun 9Jun 9