/**
 * engine.ts — node-llama-cpp integration: model loading, identity, and
 * corpus embedding.
 *
 * Uses node-llama-cpp DIRECTLY (the same engine dependency
 * harper-fabric-embeddings/HFE wraps for Harper) rather than going through
 * HFE — flair-bench has to run with no Flair/Harper installation at all, so
 * it can't depend on the Harper-only wrapper package. See prefixes.ts for
 * how the nomic search-prefix convention HFE applies is replicated here.
 */
import { type Llama, type LlamaModel } from "node-llama-cpp";
import type { BenchProgressEvent, CorpusInfo, ModelBenchResult, ModelIdentity } from "./types.js";
/** Shared Llama instance for the whole batch run — one backend/GPU detection, reused across every model load. */
export declare function getSharedLlama(): Promise<Llama>;
export declare function corpusInfo(): CorpusInfo;
export declare function computeModelIdentity(model: LlamaModel, filePath: string): Promise<ModelIdentity>;
/**
 * Full single-model benchmark: load, embed the corpus, exact-cosine rank
 * every query, score p@3/MRR overall and per-kind. Disposes the model
 * before returning so a batch run's next model starts from a clean slate.
 *
 * Peak-RSS baseline is captured BEFORE `llama.loadModel()` runs — sampling
 * only from inside the embedding phase (an earlier version of this
 * function did that) would already have the model's own weights resident
 * in the baseline, silently undercounting the number the spec actually
 * wants ("how much memory does loading+using this model cost"). Verified
 * against the Q4 baseline: an 80 MiB GGUF was reporting a ~24 MiB delta
 * before this fix, because mmap'd model weight pages had already been
 * counted into the baseline by the time sampling started.
 */
export declare function benchModel(llama: Llama, filePath: string, options?: {
    warmupN?: number;
    onProgress?: (e: BenchProgressEvent) => void;
    index?: number;
    total?: number;
}): Promise<ModelBenchResult>;