Valkey 9.2 Released with Enhanced AI Inference and Caching Features
Article Content
- •Valkey 9.2 claims up to 40% reduction in AI inference costs.
- •New features include replication compression and forkless snapshots.
- •The update aims to optimize GPU resource usage across distributed systems.
Valkey 9.2 was released on November 19, 2026, introducing significant improvements in distributed key-value caching and AI inference capabilities. The update claims to reduce AI inference costs by up to 40% and time-to-first-token by up to 80%. Key features include replication compression that decreases cross-region traffic by 50-65% and forkless snapshots that eliminate memory doubling during in-memory backups. The release also enhances large sorted sets, improving update speeds by 105% while using 36-43% less memory. This version aims to optimize GPU resource utilization by allowing inference engines to reuse cached work instead of recomputing it. Valkey is governed by the Linux Foundation and has gained contributions from major tech companies like AWS, Google Cloud, and Oracle. The project is positioned as both an AI infrastructure and a general-purpose datastore.
Ask AI about this cluster
Answers cite the sources they use
Timeline
More articles in this cluster (2)
Common questions
What are the main improvements in Valkey 9.2?
How does Valkey 9.2 affect existing hardware?
Is there any immediate action required for users?
Continue Reading
Lazarus Group Targets 30 South Korean Servers Using PHP Vulnerabilities North Korea-linked Lazarus Group has targeted 30 servers in South Korea as part of a larger cyber operation involving 581 servers across 10 countries. The attacks exploit two critical remote code execution vulnerabilities in PHP (CVE-2026-109618 and CVE-2026-109619), allowing unauthorized server command execution. The…