INT21 称在 8×B200 上跑 DeepSeek V4.1 Flash 达 1700+ tok/s

INT21 @int21_ai原推发布于 2026.10.27

在 X 上打开原推

Once attackers get inside a network, they can reach other systems in under 30 minutes, and within 27 seconds. Most organizations won’t spot an intrusion in that window, let alone stop it. Defenders need AI agents that are faster than the attackers. That takes ultrafast inference, so each agent reasons faster, and collaborative agent swarms, so many agents chase every lead at once. We've built both. Our agent swarms have built inference engines that run DeepSeek v4.1 Flash at 1,700+ tokens/sec on 8×B200. If you’re defending an enterprise network and need to outpace attackers, INT21 can help. Reach out at info@int21.ai. More about our approach: https://int21.ai/insights/ultrafast-inference-agent-swarms-the-future-of-cyber-defense