Fal, Together and Baseten are buying their own Nvidia chips, The Information reports
Fal is buying Nvidia chips for leased data centres, its data-centre lead told The Information, and Together and Baseten are moving the same…
Topic
Baseten
Baseten publishes a Rust and CUDA engine for DeepSeek V4.1 Flash, citing 2,060 tokens a second
Baseten says its engine decodes 2,060 tokens a second on eight B300 GPUs, with a 1M-token prefill in 11.7 seconds. The code is…