Everything tagged #llm
6 articles, newest first.
CAG Over RAG, When Speed Is the Constraint
RAG searches for information on every turn. CAG pre-computes the KV cache. Where Time-to-First-Token and conversational latency matter, caching flips the architecture.
Are LLMs Actually Thinking?
Tokens, vectors, attention, and next-token prediction. What is actually happening underneath something that feels like a conversation.
Running Google's Gemma Through Hugging Face
Gemma is capable and open source. Hugging Face is what makes getting to it straightforward.
Fine-Tuning Large Language Models: PEFT, LoRA, and QLoRA in Practice
Full parameter training requires clusters of H100s. Parameter-Efficient Fine-Tuning (PEFT) with low-rank matrix decomposition brings specialized adaptation to a single GPU.
Google's Gemini 1.5 Pro API: Multimodal Intelligence and 2M Token Context
Massive context windows, native multimodality, and structured schema outputs: how developers can build production systems on Google AI Studio.
How Retrieval-Augmented Generation Works
A vector database, cosine similarity, and an LLM context injection. The mathematical and code mechanics of grounding language models.
