SubQ Snap 决策模型以 660ms 处理 100K token 上下文
SubQ Snap 决策模型在 100K token 上下文下延迟 660ms，384K token 下为 2.5 秒，约 3.84 倍输入对应 3.8 倍耗时，接近线性扩展，而标准二次注意力在该区间注意力开销约上升 15 倍。
Decision models deserve more attention than they get.
look at the latency numbers on SubQ Snap from @subquadratic
660ms for 100K tokens. 2.5 seconds for 384K. that’s about 3.8x the time for 3.84x the input, which is what linear scaling looks like. with standard quadratic attention, the attention cost alone would rise about 15x over that range.
that scaling is how a decision model can hold 384K tokens of code, docs, logs and screenshots in one call, when most stop at 32K to 64K and make you chunk.
$0.05 per million input tokens, output free.
many of the existing decision models have mostly been short-context tools. 32K tokens is enough to classify a ticket, but too little to judge a change against a whole codebase.
Now that changed.
来源：rohanpaul_ai · x.com