DEV Community

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The LiteLLM Supply Chain Attack Broke Trust in Python-Based AI Infrastructure

The LiteLLM Supply Chain Attack Broke Trust in Python-Based AI Infrastructure

6
Comments
7 min read
vLLM On-Demand Gateway: Zero-VRAM Standby for Local LLMs on Consumer GPUs

vLLM On-Demand Gateway: Zero-VRAM Standby for Local LLMs on Consumer GPUs

1
Comments
4 min read
The Real Cost of Your AI Agent (It's Not What You Think)

The Real Cost of Your AI Agent (It's Not What You Think)

Comments
6 min read
What a Token Audit Actually Finds in Production Agent Systems

What a Token Audit Actually Finds in Production Agent Systems

Comments
3 min read
Why Your AI Agent Can't Check Its Own Work (and How to Fix It)

Why Your AI Agent Can't Check Its Own Work (and How to Fix It)

Comments
3 min read
I audited LangGraph's default patterns for token efficiency. Score: 39/100.

I audited LangGraph's default patterns for token efficiency. Score: 39/100.

Comments
6 min read
Local LLM Acceleration: Quantization, TTS, and 1M Tokens/Sec

Local LLM Acceleration: Quantization, TTS, and 1M Tokens/Sec

Comments
4 min read
Designing Agent Fleets That Survive Rate Limits: A Production Architecture Guide

Designing Agent Fleets That Survive Rate Limits: A Production Architecture Guide

Comments
6 min read
pen Source Project of the Day (Part 23): PageLM - Open-Source AI Education Platform, Turning Learning Materials into Interactive Resources

pen Source Project of the Day (Part 23): PageLM - Open-Source AI Education Platform, Turning Learning Materials into Interactive Resources

1
Comments
6 min read
I Replaced Cloud AI APIs With a $600 Mac Mini — Here's What Actually Works

I Replaced Cloud AI APIs With a $600 Mac Mini — Here's What Actually Works

1
Comments
4 min read
The Ultimate Guide: Installing Ollama on Fedora 43

The Ultimate Guide: Installing Ollama on Fedora 43

1
Comments
3 min read
Multi-Agent Systems Break Differently Than Single Agents

Multi-Agent Systems Break Differently Than Single Agents

Comments
7 min read
Why Your Agent's Eval Suite Won't Catch Production Failures

Why Your Agent's Eval Suite Won't Catch Production Failures

Comments
6 min read
Evaluate LLM code generation with LLM-as-judge evaluators

Evaluate LLM code generation with LLM-as-judge evaluators

6
Comments
12 min read
When Code Becomes Cheap, Thinking Becomes Expensive

When Code Becomes Cheap, Thinking Becomes Expensive

1
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.