Engineering Insights

DigitalOcean Gradient™ AI Platform Now Integrates with LlamaIndex

We’re excited to announce that DigitalOcean Gradient™ AI Platform now integrates natively with LlamaIndex - one of the most popular frameworks for building RAG applications. This means you can now connect your Gradient AI Platform Knowledge Base and LLMs directly to LlamaIndex workflows, using the abstractions you already know. No additional infrastructure. No complex setup. Just install two packages and start building. Why This Matters If you’ve built RAG applications before, you know the drill

Unlock Massive Token Throughput with GPU Fractioning in NVIDIA Run:ai

As AI workloads scale, achieving high throughput, efficient resource usage, and predictable latency becomes essential. NVIDIA Run:ai addresses these challenges... As AI workloads scale, achieving high throughput, efficient resource usage, and predictable latency becomes essential. NVIDIA Run:ai addresses these challenges through intelligent scheduling and dynamic GPU fractioning. GPU fractioning is wholly delivered by NVIDIA Run:ai in any environment—cloud, NCP, and on-premises. This post presen

Topping the GPU MODE Kernel Leaderboard with NVIDIA cuda.compute

Python dominates machine learning for its ergonomics, but writing truly fast GPU code has historically meant dropping into C++ to write custom kernels and to... Python dominates machine learning for its ergonomics, but writing truly fast GPU code has historically meant dropping into C++ to write custom kernels and to maintain bindings back to Python. For most Python developers and researchers, this is a significant barrier to entry. Frameworks like PyTorch address this by implementing kernels in

IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST

How NVIDIA Extreme Hardware-Software Co-Design Delivered a Large Inference Boost for Sarvam AI’s Sovereign Models

As global AI adoption accelerates, developers face a growing challenge: delivering large language model (LLM) performance that meets real-world latency and cost... As global AI adoption accelerates, developers face a growing challenge: delivering large language model (LLM) performance that meets real-world latency and cost requirements. Running models with tens of billions of parameters in production, especially for conversational or voice-based AI agents, demands high throughput, low latency, a

Designing A Streak System: The UX And Psychology Of Streaks

What makes streaks so powerful and addictive? To design them well, you need to understand how they align with human psychology. Victor Ayomipo breaks down the UX and design principles behind effective streak systems.

We Ralph Wiggumed WebStreams to make them 10x faster

When we started profiling Next.js server rendering earlier this year, one thing kept showing up in the flamegraphs: WebStreams. Not the application code running inside them, but the streams themselves. The Promise chains, the per-chunk object allocations, the microtask queue hops. After highlighted how much compute time goes into framework overhead, we started looking at where that time actually goes. A lot of it was in streams.Theo Browne's server rendering benchmarks Turns out that WebStreams

Redesigned search and filtering for runtime logs

The Runtime Logs search bar in your project dashboard has been redesigned to make filtering and exploring your logs faster and more intuitive. These improvements are available now in your project dashboard. Learn more about .runtime logs Read more When you type a filter like or , the search bar parses it into a visual pill you can read at a glance and remove with a click. Complex queries with multiple filters become easy to scan and edit without retyping anythingStructured filters.level:error