DEV Community

# llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
PFlash Boosts llama.cpp Prefill; Ollama Sees Major Speed Gains; Llama 3.2 on Android

PFlash Boosts llama.cpp Prefill; Ollama Sees Major Speed Gains; Llama 3.2 on Android

Comments
3 min read
AI is your Copilot, not to replace humans

AI is your Copilot, not to replace humans

Comments
3 min read
Your AI, Your Rules: Running a Local LLM with GPU Acceleration on Proxmox

Your AI, Your Rules: Running a Local LLM with GPU Acceleration on Proxmox

Comments
10 min read
Sentinel-Proxy AI Firewall Demo

Sentinel-Proxy AI Firewall Demo

Comments
1 min read
AI Agent Circuit Breakers: The Reliability Pattern Production Teams Are Missing

AI Agent Circuit Breakers: The Reliability Pattern Production Teams Are Missing

Comments
8 min read
When Code Stopped Being a Vibe and Started Being a Job

When Code Stopped Being a Vibe and Started Being a Job

Comments
11 min read
Using an MCP Gateway with Claude Code: A Practical Guide

Using an MCP Gateway with Claude Code: A Practical Guide

Comments 1
6 min read
What is LLM Observability? The ML Engineer's Practical Guide (2026)

What is LLM Observability? The ML Engineer's Practical Guide (2026)

1
Comments
14 min read
Claude-pilled: why complex agent workflows are working against you

Claude-pilled: why complex agent workflows are working against you

Comments
4 min read
I mapped LangChain Core as a knowledge graph — here's what the structure reveals

I mapped LangChain Core as a knowledge graph — here's what the structure reveals

1
Comments
2 min read
Beyond RAG: Why I replaced similarity search with graph traversal for AI agent context

Beyond RAG: Why I replaced similarity search with graph traversal for AI agent context

2
Comments
2 min read
AI 写代码写得越溜,架构师就越值钱

AI 写代码写得越溜,架构师就越值钱

Comments
1 min read
Claude Opus 5.0: 7 Speculative Bets From the 4.x Curve

Claude Opus 5.0: 7 Speculative Bets From the 4.x Curve

Comments
11 min read
How I built multi-model LLM routing on Groq's free tier

How I built multi-model LLM routing on Groq's free tier

Comments
4 min read
Strict Schema Enforcement: The Bedrock of AI Reliability

Strict Schema Enforcement: The Bedrock of AI Reliability

Comments
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.