LLM Engineering
How LLM applications get built and shipped: inference and serving, structured output, token formats, evaluation, and the libraries powering production language-model systems.
149 articles
LLM Engineering
Swark: Auto-Generating Architecture Diagrams by Feeding Your Codebase to GitHub Copilot
LLM Engineering
Open Interface: Teaching GPT-4 Vision to Drive Your Desktop with Screenshots and PyAutoGUI
LLM Engineering
Chainlit: The Python Framework That Turns LLM Scripts Into Production UIs
LLM Engineering
MoBA: How Moonshot AI Serves 1M-Token Contexts in Production with Learned Sparse Attention
LLM Engineering
Inside the LLM Post-Training Knowledge Base That 2,400+ Researchers Are Using
LLM Engineering
Search-R1: Training Language Models to Think and Search Without Supervision
LLM Engineering
AgentDojo: The Security Benchmark That Exposes LLM Agents' Achilles Heel
LLM Engineering
SEAL: Teaching Language Models to Write Their Own Training Data
LLM Engineering
Onyx: Building ChatGPT-Grade AI Search with Hybrid RAG and MCP Agents
LLM Engineering
Unsloth: How Custom Triton Kernels Make LLM Fine-Tuning Possible on Consumer GPUs
LLM Engineering
TOON: The Data Format That Makes LLMs Pay Attention to Your Tables
LLM Engineering
TheAgentCompany: The First Real-World Benchmark That Makes AI Agents Look Bad
LLM Engineering
SEC-bench: A NeurIPS Framework for Benchmarking LLM Agents Against Real Security Vulnerabilities
LLM Engineering
Heretic: Automatic Abliteration for Uncensoring Language Models
LLM Engineering
SelfCheckGPT: Catching LLM Hallucinations by Making Models Contradict Themselves
LLM Engineering
Running 70B LLMs on a 4GB GPU: How AirLLM Trades Speed for Accessibility
LLM Engineering
How Gitleaks Uses Entropy Analysis to Find Secrets Your Regex Patterns Miss
LLM Engineering
LLM Checker: Hardware-Aware Model Selection for Local AI Inference
LLM Engineering
RuVector: The Rust Vector Database That Rewrites Its Own Index
LLM Engineering
PyReason: Graph-Based Temporal Logic for Explainable AI
LLM Engineering
PlanAI: Type-Safe Graph Orchestration for Hybrid LLM Workflows
LLM Engineering
Parameter Golf: OpenAI's $1M Challenge to Train the Most Efficient Language Model in 16MB
LLM Engineering
Flash-MoE: Running a 397B Parameter Model on 48GB RAM by Streaming Experts from SSD
LLM Engineering