StepFun releases Step 3.7 Flash for efficient inference
阶跃星辰Step 3.7 Flash发布,专为高效推理设计
StepFun released Step 3.7 Flash with a 196B MoE architecture, using multi-matrix factorized attention to cut KV-cache cost to about 22% of DeepSeek models.
Why it matters: Step 3.7 Flash ships under Apache 2.0 with a KV-cache footprint about 22% of a comparable DeepSeek model, a concrete efficiency claim to test.