LLM Engineering
106 articles
LLM Engineering
Gorilla: Teaching LLMs to Actually Call APIs Without Hallucinating
LLM Engineering
Dalai: The NPX One-Liner That Brought LLaMA to Your Laptop
LLM Engineering
LitGPT: Lightning AI's No-Abstraction Approach to Production LLM Training
LLM Engineering
Onyx: Building a Self-Hosted AI Platform That Doesn't Lock You Into Vendor Hell
LLM Engineering
Building Better LLM Benchmarks: Inside OpenAI's Evals Framework
LLM Engineering
verl: Building Production-Grade RLHF Pipelines with Hybrid-Controller Architecture
LLM Engineering
Guidance: Programming Language Models Like They're Python Objects
LLM Engineering
Microsoft's UniLM: The Foundation Model Laboratory That Birthed 1-Bit Transformers
LLM Engineering
Repomix: The CLI Tool That Turns Your Entire Codebase Into a Single LLM-Ready File
LLM Engineering
Haystack: Why Explicit Pipelines Beat Magic Abstractions in Production RAG
LLM Engineering
SGLang: How RadixAttention and Prefix Caching Are Reshaping LLM Serving at Scale
LLM Engineering
Stanford Alpaca: How $500 and Synthetic Data Sparked the Open LLM Revolution
LLM Engineering
BitNet.cpp: Running 100B Parameter Models on Your Laptop at Human Reading Speed
LLM Engineering
Open-Assistant: How LAION Crowdsourced the First Open RLHF Dataset for Conversational AI
LLM Engineering
GPT4All: Running Production LLMs on a 2012 Laptop
LLM Engineering
Inside awesome-llm-apps: A Living Catalog of 40+ Production-Ready LLM Patterns
LLM Engineering
Inside Hyperspace AGI: Building a Peer-to-Peer Network Where AI Agents Autonomously Research Themselves
LLM Engineering
Running a 397B Parameter Model on a Laptop: How Flash-MoE Streams Experts from SSD
LLM Engineering
Parameter Golf: Training Language Models Under Extreme Memory Constraints
LLM Engineering
PlanAI: Type-Safe Workflow Orchestration for Hybrid LLM and Traditional Compute
LLM Engineering
RuVector: The Vector Database That Learns From Your Queries
LLM Engineering
PyReason: Temporal Logic Reasoning Over Knowledge Graphs with Explainability Built In
LLM Engineering
NullClaw: A 678KB AI Assistant That Boots in 8 Milliseconds
LLM Engineering