📰 Dev.to · xbill

Plain Gemma 4 26B read by its label probabilities against DiffusionGemma's one-step read, both as community 4-bit (AWQ) builds on one EC2 L4, on 1,200 labelled

Plain Gemma 4 26B read by its label probabilities against DiffusionGemma's one-step read, both as community 4-bit (AWQ) builds on one EC2 L4, on 1,200 labelled

A local-first CLI that scans Google Cloud projects for unused resources, prices each one from the Cloud Billing Catalog API, and drafts the cleanup. One call pe

A cost report gets read twice: once by a person in a terminal, once by an agent through an MCP server. Making the server compute every total instead of handing

Step by step: one Python MCP server with four read-only Apache Iceberg tools, pointed at Polaris, BigLake, OneLake, Glue, S3 Tables and Horizon by changing one

Step by step: one Python MCP server with four read-only Apache Iceberg tools, pointed at Polaris, BigLake, OneLake, Glue, S3 Tables and Horizon by changing one

An agent proposes watering the crops, a human Cabinet approves in a picture-button Studio, and Sanity Workflows waters and harvests. Plus a stopwatch on three w

Serving Gemma 4 E2B q4_0 through llama.cpp on one laptop, twice: CPU-only and on a 2021-era 4 GB GTX 1650 Ti. Same GGUF, same binary, same prompts, one flag apa

Four read-only Apache Iceberg tools bound into Google ADK, AWS Strands and Microsoft Agent Framework, run against five catalogs, 360 timed runs. Building the ag

vLLM, JAX and PyTorch serving the same Gemma 4 E2B checkpoint on the same AWS G5g GPU, on one harness and one statistic. The decode ranking reverses on boot tim

vLLM, JAX and PyTorch serving the same Gemma 4 E2B checkpoint on the same AWS G5g GPU, on one harness and one statistic. The decode ranking reverses on boot tim

A Claude Code skill that turns one markdown file into dev.to, AWS Builder Center, Medium and LinkedIn versions, checks them before they ship, and posts the ones

Serving Gemma 4 E2B in pure JAX on AWS g5g.2xlarge and g6.2xlarge with a byte-identical payload. The older instance loses 87% of decode to dtype conversion, and

One hand-written Gemma 4 port, no PyTorch and no vLLM, on two NVIDIA GPUs a generation apart. Most of it ports untouched. Two things do not, and one of them was

Gemma 4 E2B on the two cheapest whole-GPU CUDA instances AWS sells. Same Turing GPU, different host CPU. One is cheaper per hour, the other is cheaper per token

This article is about running a hand-written Gemma 4 port in pure JAX on three different...

This article provides a step by step deployment guide for serving Google's Gemma 4 on an AWS EC2 G5g...

Comparing Agent Cards with A2A - This tutorial aims to fetch the agent card from A2A agents running...

This article provides a step by step look at the A2A agent card a Strands agent publishes on Amazon...

The same research agent built three times — Google ADK on Cloud Run, Strands on Bedrock AgentCore, Agent Framework on Container Apps — all speaking A2A v1.0. Wh

A step by step guide to running a Strands agent on Amazon Bedrock AgentCore Runtime, serving the A2A protocol to callers on Google Cloud and Azure, with no AWS

All three hyperscalers now ship an agent framework, and all three speak A2A. The protocol page will...

A Strands agent on Bedrock AgentCore Runtime serving A2A to callers on Google Cloud and Azure. The AgentCore container contract, the request header it drops, wh

vLLM on TPU cannot load the Gemma 4 E2B QAT exports. So I served them from a hand-rolled JAX engine on a single v6e chip — and found that the thing that actuall