fal· fal platform

fal achieved 16 times higher throughput on Qwen3.6 for the Ideogram V4 prompt expander using DSpark on SGLang, reaching 700 tok/s after retraining a DFlash model on 250K prompt expansion samples from their fine-tuned 35B MoE model.

From the source

At @fal , we've achieved 16 times higher throughput on Qwen3.6 for a use-case that required high interactivity per user using DSpark on SGLang.

blog.fal.ai