⚙️ MLOps - antidmg · Scour

MCAP: Deployment-Time Layer Profiling for Memory-Constrained LLM Inference 🤖LLMs

Flow generation through natural language: An agentic modeling approach (11 minute read) 🛠️AI Dev Tools

shopify.engineering·1d

The Inference Economy: Token Use 🤖LLMs

frontierai.substack.com·9h·Substack

LLM Quantization 🤖LLMs

huggingface.co·3h·Hacker News

Three Cobblers, One Zhuge Liang: Making Cheaper Models Work Together 🛠️AI Dev Tools

markhuang.ai·1d·Hacker News

How AI-Driven Kubernetes Optimization Reclaimed Millions from 47% Idle Capacity 📐System Design

engineering.salesforce.com·7h

An Empirical Study of Methods for SFTing Opaque Reasoning Models 🤖LLMs

lesswrong.com·6d

AmSach/kvquant: Drop-in KV cache compressor for local LLM inference - Run 70B models on 8GB RAM 🤖LLMs

github.com·15h·DEV

Introducing DigitalOcean AI-Native Cloud for Production AI Workloads 🏗️Infrastructure

digitalocean.com·2d

AI Infrastructure Architect · Builder · Author 🛠️AI Dev Tools

markferraz.com·8h·Hacker News

Prometheus-based Grafana Server Monitoring ｜ fernvenue's Blog 📊Observability

blog.fernvenue.com·3h

What agentic AI borrowed from microservices (and made worse) 📐System Design

temporal.io·1d·Hacker News

Monitoring LLM behavior: Drift, retries, and refusal patterns 🛠️AI Dev Tools

venturebeat.com·5d·Hacker News

The Data Layer Tax for Robot Learning 🤖LLMs

rerun.io·14h·Hacker News

Our evaluation of OpenAI’s GPT-5.5 cyber capabilities 🛠️AI Dev Tools

simonwillison.net·4h

Caltech’s PrismML shrinks AI models to fit your phone without losing their mind 🤖LLMs

startupfortune.com·2d

Building Document Pipelines That Actually Scale 📐System Design

Self-hosting Upgrade: planning my first 3-node cluster for deployment in a data center 📐System Design

lemmy.world·5h

Build Strands Agents with SageMaker AI models and MLflow 🛠️AI Dev Tools

aws.amazon.com·3d

Best Practices for inference on Edge AI MCUs 📐System Design

embedded.com·1d

Log in to enable infinite scrolling