注册并分享邀请链接,可获得视频播放与邀请奖励。

DeepInfra
@DeepInfra
Fast ML inference. Run top AI models using a simple API.
加入 February 2023
76 正在关注    6K 粉丝
Encoder-decoder is back 😈!!! In DeepSeek V4.1 Flash the first 20 layers build the global KV that the next 20 read from, so prefill costs about half. Rolled out over the last 24h: throughput doubled, and we are approaching 1T tokens/day on OpenRouter. 30% off to celebrate. Enjoy. Cheapest on the market, as always.
显示更多