[dev_hugepages]

Probably a provider thing. Looking at https://help.kagi.com/kagi/ai/llms-privacy.html, they're using deepinfra.

Looking at https://openrouter.ai/deepseek/deepseek-v4-flash/providers tells us that the deepseek provider achieves 49tps of throughput while deepinfra 19tps.

[jiehong]

Thanks for taking the time to provide this info. I appreciate it