InfoQ - Performance

Microsoft Commits Maia to Multi-Gigawatt Inference, and its Efficiency Metric Draws Questions

Steef-Jan Wiggers — Fri, 16 Oct 2026 06:02:00 GMT

Microsoft will scale its Maia accelerator family to multi-gigawatt deployments from 2027, making it the primary inference system for its own products. Maia 300 collapses scale-up and scale-out onto one Ethernet fabric and moves KV state between prefill and decode workers without leaving it. Practitioners have questioned the tokens-per-watt claim that leads the announcement.

By Steef-Jan Wiggers

Instagram Modernized its UI with an AI-Native Architecture, Cutting Token Costs by 33%

Sergio De Simone — Thu, 15 Oct 2026 16:00:00 GMT

Instagram Direct migrated its Android UI from the legacy Android View system to Jetpack Compose, creating an AI-native UI codebase that is easier for AI coding agents to understand, modify, and maintain. According to Instagram engineers, the migration reduced UI code volume by 50% and token costs per AI agent session by 33%.

By Sergio De Simone

Presentation: How Eve Online Leverages Head Based Sampling to Observe "Fun"

Nicholas Herring — Tue, 13 Oct 2026 11:00:00 GMT

Nicholas Herring shares how EVE Online tackles distributed tracing and observability across a 20-year-old MMO architecture. He discusses leveraging head-based, dynamic exponential moving average (EMA), and deterministic sampling techniques to maintain high system fidelity, control telemetry costs, and avoid performance degradation under high-throughput real-time game simulations.

By Nicholas Herring

Article: When Should You Use Liquid Clustering? Benchmarking Lakehouse Layout Strategies

Kushal Kumar Vishwakarma — Mon, 12 Oct 2026 11:00:00 GMT

Physical data layout is one of the most consequential decisions in lakehouse engineering. The author compares Liquid Clustering, ZOrdering, and partitioning across four workload types on Delta Lake, uncovering two undocumented failure modes that likely affect production systems today and offering a decision framework for choosing the right layout strategy.

By Kushal Kumar Vishwakarma

Github Migrates Copilot Runtime to Rust with AI-Assisted Rewrite

Leela Kumili — Fri, 09 Oct 2026 14:29:00 GMT

GitHub migrated more than 800,000 lines of Copilot runtime code from TypeScript and Node.js to Rust in about 14.5 weeks using AI-assisted development. The incremental migration used N-API interoperability, automated testing, human review, and 128 pull requests while continuing to ship releases.

By Leela Kumili

Presentation: Ontology‐Driven Observability: Building the E2E Knowledge Graph at Netflix Scale

Prasanna Vijayanathan, Renzo Sanchez-Silva — Fri, 09 Oct 2026 11:00:00 GMT

Prasanna Vijayanathan and Renzo Sanchez-Silva share how Netflix tackles observability across 38M events/sec. They discuss replacing reactive monitoring with an AI-driven operational ontology and agentic workflows using Claude and graph databases. They explain how unifying MELT telemetry into queryable knowledge graphs enables automated triaging, root-cause analysis, and self-healing systems.

By Prasanna Vijayanathan, Renzo Sanchez-Silva