1+ hour, 21+ min ago   (459+ words) Ads recommendation systems must retrieve and rank thousands of ads within milliseconds, processing millions of candidates per second. To manage this scale, some approaches to sequence models rely on hybrid model configurations where a specific model processes user event sequences…...

3+ week, 5+ day ago   (449+ words) Meta’s ads serving fleet handles more than 5 million requests per second on average at the serving platform entry point, which is over 400 billion per day across all monetized surfaces1. Every millisecond shaved off the p99 latency makes the ads more relevant for…...

1+ mon, 4+ day ago   (365+ words) Modern AI workloads are “data hungry” and have very different workload characteristics than traditional web applications: bursty and sustained high throughput, predictable and bounded pMax latencies, and variable I/O patterns. The focus for BLOB storage, in recent years, has…...

1+ mon, 1+ week ago   (1660+ words) This is the everyday problem behind privacy-aware infrastructure (PAI): The inputs are noisy and probabilistic, but the outputs need to be precise enough to drive enforcement. AI-native products make that problem harder. They introduce new data modalities, faster iteration cycles,…...

2+ mon, 1+ week ago   (814+ words) However, the microservice based design had hard constraints on model complexity and the number of candidates evaluated, ultimately creating a ceiling on the quality of recommendations that people on our platforms see. To break through this ceiling, we’ve fully reimagined…...

2+ mon, 3+ week ago   (178+ words) On its face the new Friend Bubbles feature looks simple enough. It highlights Reels your friends have watched and reacted to. But sometimes the features that seem the most straightforward require the deepest engineering work. On this episode of the…...

2+ mon, 3+ week ago   (901+ words) We’ve recently revamped our data ingestion system’s architecture to significantly enhance its efficiency and reliability. The new architecture moves away from customer-owned pipelines, which functioned effectively at a small scale, to a simpler self-managed data warehouse service that still operates…...

3+ mon, 4+ day ago   (445+ words) The HSM-based Backup Key Vault Meta’s HSM-based Backup Key Vault provides the foundation for end-to-end encrypted backups for WhatsApp and Messenger. The system allows people to protect their backed-up message history with a recovery code, ensuring that the recovery code…...

3+ mon, 2+ week ago   (423+ words) People struggle with three friction points when searching for answers in community content – discovery, consumption, and validation. We needed a system where searching for an “Italian coffee drink” effectively matches a post about “cappuccino,” even if the word “coffee” is…...

3+ mon, 2+ week ago   (537+ words) Here’s how it works and where we’re headed: When the code you ship serves more than 3 billion people, even a 0.1% performance regression can translate to significant additional power consumption. In Meta’s Capacity Efficiency organization, we see efficiency as a two-sided…...