PD Serving of Qwen3.8-2.4T
How vLLM reaches 5K throughput and 180 interactivity on Qwen3.8-2.4T with GB300 NVL72 PD serving and how to reproduce results yourself.
// Company Updates
All companiesFrom the Industry Leaders
Can Jev Be a Better Agent Evaluator?
We tested using Jev-as-a-Judge against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation.
RADAR: Catch gray failures with anomaly detection
Some of the most damaging outages are the ones your monitoring never flags: a slice...
Amazon SageMaker Inference: 2026 year-to-date launches in review
Amazon SageMaker AI shipped 13 inference launches in year-to-date across two deployment paths: fully managed endpoints and Amazon SageMaker HyperPod Inference. This post reviews each launch, from...
Spend Management expands to Enterprise Flexible Commitment plans
Enterprise teams on Flexible Commitment plans can now use Spend Management, already available on Pro, at no additional cost.You can set a budget at any time in Spend Management settings.Set a budget...
WebMCP support now available in mcp-handler
mcp-handler now has experimental support for WebMCP, the proposed web standard for exposing tools to in-browser agents. Add a single script tag to your site, and your existing MCP tools become...
MilleMiglia: A realistic instance generator for middle-mile logistics
Algorithms & Theory
Enabling secure, productive work on personal devices
At Databricks IT, our vision is to empower people to work from anywhere without putting...
v0 now reads npm credentials from shared environment variables
v0 now installs private packages from npm and custom registries using credentials stored as shared environment variables on Vercel.This makes it easier for teams to build with their existing design...
Introducing Kimi K3 on Amazon Bedrock
Kimi K3 from Moonshot AI is now available on Amazon Bedrock, giving you a powerful new open-weight option for coding and knowledge work. It offers native vision, a 1-million-token context window, and...
Changing the game: Using agentic AI to secure infrastructure code
AI is accelerating software development at an unprecedented pace. But as code generation scales, so do the challenges of securing the code, especially emerging AI-based vulnerability exploitations....
The Next Chapter of Entertainment and Fandom
At Character.ai, our goal has always been to power new formats for users to interact with their favorite characters, stories, and communities. While leading the industry in AI safety,...
Migrating multi-model AI agents to Amazon Bedrock AgentCore runtime
Migrate a multi-model healthcare AI agent from self-managed Amazon ECS with AWS Fargate to Amazon Bedrock AgentCore runtime, preserving triple-model orchestration and vector-enhanced knowledge...
The new AgentCore runtime: Elastic, optimized, and consistently fast starts
Today we are announcing the new AgentCore runtime, a capability of Amazon Bedrock AgentCore built for the speed, flexibility, and cost efficiency that production agents demand. It reclaims memory as...
Deploy Hugging Face models on Amazon SageMaker AI with coding agents
Deploy production-ready Hugging Face models on Amazon SageMaker AI using six open-source agent skills. Point a coding agent at a model and get back a real-time endpoint with the right serving...
Introducing the Australian Youth Safety Blueprint
OpenAI introduces the Australian Youth Safety Blueprint, a six-pillar roadmap for safer AI experiences that protect and empower young people.
Postgres week in the Netherlands: PGDay Lowlands & Percona Live 2026
Notes from three days in the Netherlands, featuring a lightning talk on pg_clickhouse and pg_stat_ch at PGDay Lowlands and a session on PostgreSQL 19 monitoring at Percona Live Amsterdam.
Database Branching: A Developer's Guide to Git-Style Workflows
Git made isolated development a baseline for software teams. Each developer can create...
Announcing Server-Side Scan Planning with Starburst and Databricks
We are excited to announce that the Starburst Enterprise 481-e STS now includes support for …
Jev is the fastest-adopted model in AI Gateway history
Within 24 hours of launching on AI Gateway, Jev from TypeSafe AI reached more than twice as many paid teams as any previous model launch, making it the fastest-adopted model in gateway history.Jev...