Perplexity AI宣布自研推理引擎ROSE,用于服务从嵌入模型到各种规模的模型,提升运行时优化。
RT @perplexity_ai: We’ve developed our own inference engine Runtime-Optimized Serving Engine (ROSE) to serve models ranging from embeddings…
likes: 268 | retweets: 31 | replies: 26 | views: 17287