GoogleCloudAiplatformV1SpeculativeDecodingSpecNgramSpeculation
import type { GoogleCloudAiplatformV1SpeculativeDecodingSpecNgramSpeculation } from "https://googleapis.deno.dev/v1/aiplatform:v1.ts";N-Gram speculation works by trying to find matching tokens in the previous prompt sequence and use those as speculation for generating new tokens.
interface GoogleCloudAiplatformV1SpeculativeDecodingSpecNgramSpeculation {
ngramSize?: number;
}