kynjal-cli 4.0.0 → 4.0.1

package/dist/src/appliance/gguf-engine.d.ts

@@ -0,0 +1,91 @@
+/**
+ * ruvLLM GGUF Inference Engine -- Pure Node.js GGUF Model Interface
+ *
+ * Provides:
+ *   1. GGUF binary header parsing (metadata without loading weights)
+ *   2. Model loading abstraction (node-llama-cpp when available, metadata-only fallback)
+ *   3. Token generation interface with async iterator streaming
+ *   4. KV-cache persistence to RVF-compatible binary format
+ *
+ * Zero external dependencies. node-llama-cpp is an optional peer.
+ *
+ * @module @claude-flow/cli/appliance/gguf-engine
+ */
+export interface GgufMetadata {
+    magic: string;
+    version: number;
+    tensorCount: number;
+    kvCount: number;
+    architecture?: string;
+    name?: string;
+    contextLength?: number;
+    embeddingLength?: number;
+    blockCount?: number;
+    vocabSize?: number;
+    quantization?: string;
+    fileSize: number;
+    metadata: Record<string, unknown>;
+}
+export interface GgufEngineConfig {
+    contextSize?: number;
+    maxTokens?: number;
+    temperature?: number;
+    kvCachePath?: string;
+    verbose?: boolean;
+}
+export interface GenerateRequest {
+    prompt: string;
+    model?: string;
+    maxTokens?: number;
+    temperature?: number;
+    stream?: boolean;
+    stopSequences?: string[];
+}
+export interface GenerateResponse {
+    text: string;
+    model: string;
+    tokensUsed: number;
+    latencyMs: number;
+    metadataOnly: boolean;
+}
+/**
+ * Parse the header and metadata from a GGUF file without loading tensors.
+ * Reads only the first 256 KB of the file.
+ */
+export declare function parseGgufHeader(path: string): Promise<GgufMetadata>;
+export declare class GgufEngine {
+    private config;
+    private llamaCpp;
+    private llamaModel;
+    private llamaContext;
+    private loadedModels;
+    private activeModelPath;
+    private kvCache;
+    constructor(config: GgufEngineConfig);
+    /** Probe for node-llama-cpp availability. */
+    initialize(): Promise<void>;
+    /** Parse GGUF header and optionally load the model for inference. */
+    loadModel(path: string): Promise<GgufMetadata>;
+    /** Generate text. Delegates to node-llama-cpp or returns a metadata-only stub. */
+    generate(request: GenerateRequest): Promise<GenerateResponse>;
+    /** Stream tokens via async iterator. Falls back to yielding full response. */
+    stream(request: GenerateRequest): AsyncGenerator<string>;
+    /**
+     * Persist the KV cache to an RVF-compatible binary file.
+     * Format: RVKV magic | version u32 | model SHA-256 (32B) | entry count u32
+     *         entries: [key_len u32, key, val_len u32, val] | footer SHA-256 (32B)
+     */
+    persistKvCache(outputPath: string): Promise<void>;
+    /** Restore KV cache from an RVF-compatible binary file. */
+    loadKvCache(inputPath: string): Promise<void>;
+    /** Return metadata for all loaded models. */
+    getLoadedModels(): GgufMetadata[];
+    /** Store a key-value pair in the in-memory KV cache. */
+    setKvEntry(key: string, value: Buffer): void;
+    /** Retrieve a key-value pair from the in-memory KV cache. */
+    getKvEntry(key: string): Buffer | undefined;
+    /** Release resources, unload models, and optionally persist the KV cache. */
+    shutdown(): Promise<void>;
+    private tryLoadLlamaCpp;
+}
+//# sourceMappingURL=gguf-engine.d.ts.map

package/dist/src/appliance/gguf-engine.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"gguf-engine.d.ts","sourceRoot":"","sources":["../../../src/appliance/gguf-engine.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAmBH,MAAM,WAAW,YAAY;IAC3B,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,MAAM,CAAC;IAChB,WAAW,EAAE,MAAM,CAAC;IACpB,OAAO,EAAE,MAAM,CAAC;IAChB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,QAAQ,EAAE,MAAM,CAAC;IACjB,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;CACnC;AAED,MAAM,WAAW,gBAAgB;IAC/B,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,OAAO,CAAC,EAAE,OAAO,CAAC;CACnB;AAED,MAAM,WAAW,eAAe;IAC9B,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,MAAM,CAAC,EAAE,OAAO,CAAC;IACjB,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;CAC1B;AAED,MAAM,WAAW,gBAAgB;IAC/B,IAAI,EAAE,MAAM,CAAC;IACb,KAAK,EAAE,MAAM,CAAC;IACd,UAAU,EAAE,MAAM,CAAC;IACnB,SAAS,EAAE,MAAM,CAAC;IAClB,YAAY,EAAE,OAAO,CAAC;CACvB;AA6ED;;;GAGG;AACH,wBAAsB,eAAe,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,YAAY,CAAC,CAWzE;AAyED,qBAAa,UAAU;IACrB,OAAO,CAAC,MAAM,CAA6B;IAC3C,OAAO,CAAC,QAAQ,CAAa;IAC7B,OAAO,CAAC,UAAU,CAAa;IAC/B,OAAO,CAAC,YAAY,CAAa;IACjC,OAAO,CAAC,YAAY,CAAwC;IAC5D,OAAO,CAAC,eAAe,CAAuB;IAC9C,OAAO,CAAC,OAAO,CAAkC;gBAErC,MAAM,EAAE,gBAAgB;IAUpC,6CAA6C;IACvC,UAAU,IAAI,OAAO,CAAC,IAAI,CAAC;IAOjC,qEAAqE;IAC/D,SAAS,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,YAAY,CAAC;IAqBpD,kFAAkF;IAC5E,QAAQ,CAAC,OAAO,EAAE,eAAe,GAAG,OAAO,CAAC,gBAAgB,CAAC;IA6CnE,8EAA8E;IACvE,MAAM,CAAC,OAAO,EAAE,eAAe,GAAG,cAAc,CAAC,MAAM,CAAC;IAuB/D;;;;OAIG;IACG,cAAc,CAAC,UAAU,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IA0BvD,2DAA2D;IACrD,WAAW,CAAC,SAAS,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAmCnD,6CAA6C;IAC7C,eAAe,IAAI,YAAY,EAAE;IAEjC,wDAAwD;IACxD,UAAU,CAAC,GAAG,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,IAAI;IAE5C,6DAA6D;IAC7D,UAAU,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS;IAE3C,6EAA6E;IACvE,QAAQ,IAAI,OAAO,CAAC,IAAI,CAAC;YAiBjB,eAAe;CAI9B"}