Engineering Insights

0.134.0

Features ✨ Add support for streaming JSON Lines and binary data with yield. PR #15022 by @tiangolo. This also upgrades Starlette from >=0.40.0 to >=0.46.0, as it's needed to properly unrwap and re-raise exceptions from exception groups. New docs: Stream JSON Lines. And new docs: Stream Data. Docs 📝 Update Library Agent Skill with streaming responses. PR #15024 by @tiangolo. 📝 Update docs for responses and new stream with yield. PR #15023 by @tiangolo. 📝 Add await in StreamingResponse code ex

Security Advisory: Addressing Recent Vulnerabilities in Angular

Develop Native Multimodal Agents with Qwen3.5 VLM Using NVIDIA GPU-Accelerated Endpoints

Alibaba has introduced the new open source Qwen3.5 series built for native multimodal agents. The first model in this series is a ~400B parameter native... Alibaba has introduced the new open source Qwen3.5 series built for native multimodal agents. The first model in this series is a ~400B parameter native vision-language model (VLM) with reasoning built with a hybrid architecture of mixture of experts (MoE) and Gated Delta Networks. Qwen3.5 can understand and navigate user interfaces, which im

Cultivating a robust and efficient quantum-safe HTTPS

Posted by Chrome Secure Web and Networking Team Today we're announcing a new program in Chrome to make HTTPS certificates secure against quantum computers. The Internet Engineering Task Force (IETF) recently created a working group, PKI, Logs, And Tree Signatures (“PLANTS”), aiming to address the performance and bandwidth challenges that the increased size of quantum-resistant cryptography introduces into TLS connections requiring Certificate Transparency (CT). We recently shared our call to a

Maximizing GPU Utilization with NVIDIA Run:ai and NVIDIA NIM

Organizations deploying LLMs are challenged by inference workloads with different resource requirements. A small embedding model might use only a few gigabytes... Organizations deploying LLMs are challenged by inference workloads with different resource requirements. A small embedding model might use only a few gigabytes of GPU memory, while a 70B+ parameter LLM could require multiple GPUs. This diversity often leads to low average GPU utilization, high compute costs, and unpredictable latency.

Before You Migrate: Five Surprising Ingress-NGINX Behaviors You Need to Know

As announced November 2025, Kubernetes will retire Ingress-NGINX in March 2026. Despite its widespread usage, Ingress-NGINX is full of surprising defaults and side effects that are probably present in your cluster today. This blog highlights these behaviors so that you can migrate away safely and make a conscious decision about which behaviors to keep. This post also compares Ingress-NGINX with Gateway API and shows you how to preserve Ingress-NGINX behavior in Gateway API. The recurring risk pa

Keeping community human while scaling with agents

At Vercel, our developer community is at the heart of everything we do. It's how we stay closest to the people using what we build. As our community grew, automation helped us scale. But questions still got lost, routing took time, and context switching pulled us away from the work that actually required our expertise. And automation could never help with the things that mattered most, the moments where you really connect with someone and help them. You can't use AI to replicate the feeling of t

Vercel Queues now in public beta

is a durable event streaming system built with , and is now available in public beta for all teams. Vercel Queues also powers : use Queues for direct message publishing and consumption, Workflow for ergonomic multi step orchestration.Vercel QueuesFluid computeWorkflow Functions need a reliable way to defer expensive work and guarantee that tasks complete even when functions crash or new deployments roll out. Queues makes it simple to process messages asynchronously with automatic retries and del