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.
157 articles
LLM Engineering
Zep: Why Temporal Knowledge Graphs Beat Vector Databases for AI Agent Memory
LLM Engineering
Red-Teaming LLMs with Systematic Prompt Perturbation: Inside Fiddler Auditor
LLM Engineering
How Large Language Models Are Learning to Think in Graphs: A Research Taxonomy
LLM Engineering
Running Mixtral-8x7B on Consumer Hardware: Expert Offloading and Mixed Quantization
LLM Engineering
Mangio-RVC-Fork: When Voice Conversion Meets Ensemble Pitch Detection
LLM Engineering
Axolotl: The Config-Driven LLM Fine-Tuning Framework Racing Ahead of Research
LLM Engineering
LLM Sherpa: How Smart Chunking Fixes RAG's Biggest Problem
LLM Engineering
RepEng: Steering Language Models in Seconds Without Fine-Tuning
LLM Engineering
LLMFuzzer: Security Testing for the Application-LLM Boundary
LLM Engineering
Inside pallms: A Security Arsenal for Breaking LLM Guardrails
LLM Engineering
Guidance: Programming with LLMs Like They're Regular Expressions
LLM Engineering
SGLang: How RadixAttention and Prefix Caching Achieve 5x Faster LLM Inference
LLM Engineering
Medusa: Accelerating LLM Inference by Predicting Multiple Tokens in Parallel
LLM Engineering
mergekit: Combining LLMs Without Training by Operating in Weight Space
LLM Engineering
Building a Prompt Injection Firewall: Inside Vigil's Multi-Layer Defense System
LLM Engineering
How GPT-2 Leaks Its Training Data: A Deep Dive into Language Model Memorization
LLM Engineering
Inside Microsoft's Responsible AI Toolbox: A Widget Architecture for Model Accountability
LLM Engineering
LLM OSINT: When AI Becomes a Digital Private Investigator
LLM Engineering
LLM Canary: OWASP-Aligned Security Testing for Language Models
LLM Engineering
ModelScan: Detecting Malicious Code in ML Models Before It Executes
LLM Engineering
BIG-bench: Google's 200+ Task Gauntlet for Language Model Evaluation
LLM Engineering
OpenVLA: Training Vision-Language-Action Models That Actually Manipulate Objects
LLM Engineering
How a Single Adversarial Image Can Jailbreak Vision-Language Models
LLM Engineering