ThunderAgent: 2x Faster Agentic Inference for Synthetic Data Generation at Scale

Together AI Version 1 original current

Imported from official source

ThunderAgent is a program-aware scheduler for agentic inference. By treating each agent workflow as a schedulable program, it eliminates KV cache thrashing to deliver more than 2x single-node throughput and near-linear multi-node scaling.

This version

Version
1 of 1
Recorded
September 20, 2026 19:52
Change
Initial
Content hash
756765418a39e4891c16daf27b5b632a
All versions
Revision history

Officially records where a publication came from, not whether it is true. Imported records are reproduced from an organization's own official source.