@qvac/sdk 0.8.0 → 1.0.0

package/dist/client/rpc/profiling/profiler.js

@@ -1,139 +0,0 @@
-import { nowMs, record, recordPhase, recordServerBreakdownPhases, recordDelegationBreakdownPhases, } from "../../../profiling/index.js";
-import { getGlobalSingleton } from "../../../utils/global-singleton.js";
-const CONNECTION_TRACKING_STATE_KEY = Symbol.for("@qvac/sdk:rpc-connection-tracking-state");
-function getConnectionTrackingState() {
-    return getGlobalSingleton(CONNECTION_TRACKING_STATE_KEY, () => {
-        return {
-            connectionTimeRecorded: false,
-            pendingConnectionTimeMs: undefined,
-        };
-    });
-}
-function recordRequestPhases(base, timings) {
-    recordPhase(base, "request.zodValidation", timings.requestZodValidationMs);
-    recordPhase(base, "request.stringify", timings.requestStringifyMs);
-    if (timings.requestZodValidationMs !== undefined &&
-        timings.requestStringifyMs !== undefined) {
-        recordPhase(base, "request.totalSerialization", timings.requestZodValidationMs + timings.requestStringifyMs);
-    }
-}
-function createBaseTimings(profileId, requestType) {
-    return { profileId, requestType, requestStart: nowMs() };
-}
-export function createClientTimings(profileId, requestType) {
-    return createBaseTimings(profileId, requestType);
-}
-export function createClientStreamTimings(profileId, requestType) {
-    return { ...createBaseTimings(profileId, requestType), chunkCount: 0 };
-}
-export function cacheConnectionTime(durationMs) {
-    const state = getConnectionTrackingState();
-    if (state.connectionTimeRecorded)
-        return;
-    if (state.pendingConnectionTimeMs !== undefined)
-        return;
-    state.pendingConnectionTimeMs = durationMs;
-}
-export function flushConnectionTime() {
-    const state = getConnectionTrackingState();
-    if (state.connectionTimeRecorded)
-        return;
-    if (state.pendingConnectionTimeMs === undefined)
-        return;
-    const durationMs = state.pendingConnectionTimeMs;
-    state.pendingConnectionTimeMs = undefined;
-    state.connectionTimeRecorded = true;
-    record({
-        ts: nowMs(),
-        op: "rpc",
-        kind: "rpc",
-        phase: "connection",
-        ms: durationMs,
-    });
-}
-export function recordClientEvents(timings, serverMeta) {
-    const now = nowMs();
-    const totalClientTime = now - timings.requestStart;
-    const base = {
-        ts: now,
-        op: timings.requestType,
-        kind: "rpc",
-        profileId: timings.profileId,
-    };
-    recordRequestPhases(base, timings);
-    // For unary requests, this measures send → full response received
-    if (timings.sendStart !== undefined &&
-        timings.firstResponseAt !== undefined) {
-        recordPhase(base, "serverWait", timings.firstResponseAt - timings.sendStart);
-    }
-    recordPhase(base, "response.jsonParse", timings.responseJsonParseMs);
-    recordPhase(base, "response.zodValidation", timings.responseZodValidationMs);
-    if (timings.responseJsonParseMs !== undefined &&
-        timings.responseZodValidationMs !== undefined) {
-        recordPhase(base, "response.totalParsing", timings.responseJsonParseMs + timings.responseZodValidationMs);
-    }
-    recordPhase(base, "totalClientTime", totalClientTime);
-    if (serverMeta?.server) {
-        recordServerBreakdownPhases(base, serverMeta.server, "server");
-        if (serverMeta.server.totalServerMs !== undefined) {
-            recordPhase(base, "clientOverhead", Math.max(0, totalClientTime - serverMeta.server.totalServerMs));
-        }
-    }
-    if (serverMeta?.delegation) {
-        recordDelegationBreakdownPhases(base, serverMeta.delegation);
-    }
-    if (serverMeta?.operation) {
-        recordOperationEvent(serverMeta.operation);
-    }
-}
-function recordOperationEvent(op) {
-    const event = {
-        ts: nowMs(),
-        op: op.op,
-        kind: op.kind,
-        ms: op.ms,
-    };
-    if (op.profileId !== undefined)
-        event.profileId = op.profileId;
-    if (op.gauges !== undefined)
-        event.gauges = op.gauges;
-    if (op.tags !== undefined)
-        event.tags = op.tags;
-    if (op.count !== undefined)
-        event.count = op.count;
-    record(event);
-}
-export function recordClientStreamEvents(timings, serverMeta) {
-    const now = nowMs();
-    const totalClientTime = now - timings.requestStart;
-    const base = {
-        ts: now,
-        op: timings.requestType,
-        kind: "rpc",
-        profileId: timings.profileId,
-    };
-    recordRequestPhases(base, timings);
-    if (timings.sendStart !== undefined && timings.firstChunkAt !== undefined) {
-        recordPhase(base, "ttfb", timings.firstChunkAt - timings.sendStart);
-    }
-    if (timings.firstChunkAt !== undefined && timings.lastChunkAt !== undefined) {
-        recordPhase(base, "streamDuration", timings.lastChunkAt - timings.firstChunkAt);
-    }
-    recordPhase(base, "totalClientTime", totalClientTime, {
-        count: timings.chunkCount,
-    });
-    if (serverMeta?.server) {
-        recordServerBreakdownPhases(base, serverMeta.server, "server");
-    }
-    if (serverMeta?.delegation) {
-        recordDelegationBreakdownPhases(base, serverMeta.delegation);
-    }
-    if (serverMeta?.operation) {
-        recordOperationEvent(serverMeta.operation);
-    }
-}
-export function resetConnectionTracking() {
-    const state = getConnectionTrackingState();
-    state.connectionTimeRecorded = false;
-    state.pendingConnectionTimeMs = undefined;
-}

package/dist/constants/registry.d.ts

@@ -1,2 +0,0 @@
-export declare const DEFAULT_REGISTRY_CORE_KEY = "uf1fm44uzockp6azhcdiqt1esjgm65fwtimsh946e8kwysdes9ko";
-//# sourceMappingURL=registry.d.ts.map

package/dist/constants/registry.js

@@ -1 +0,0 @@
-export const DEFAULT_REGISTRY_CORE_KEY = "uf1fm44uzockp6azhcdiqt1esjgm65fwtimsh946e8kwysdes9ko";

package/dist/examples/cache-management.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=cache-management.d.ts.map

package/dist/examples/cache-management.js

@@ -1,97 +0,0 @@
-import { WHISPER_TINY } from "../models/registry/index.js";
-import { downloadAsset, getModelInfo, loadModel, unloadModel } from "..";
-const printModelStatus = (info, label) => {
-    console.log(`\n${label}`);
-    console.log(`   Model Name: ${info.name}`);
-    console.log(`   Model ID: ${info.modelId}`);
-    console.log(`   Blob Core Key: ${info.blobCoreKey?.substring(0, 16) || "N/A"}...`);
-    console.log(`   Expected Size: ${(info.expectedSize / 1024 / 1024).toFixed(2)} MB`);
-    console.log(`   Addon: ${info.addon}`);
-    console.log(`   Cache Files: ${info.cacheFiles.length}`);
-    console.log(`   Is Cached: ${info.isCached ? "✅" : "❌"}`);
-    console.log(`   Is Loaded: ${info.isLoaded ? "✅" : "❌"}`);
-    if (info.isCached) {
-        if (info.cacheFiles.length === 1) {
-            console.log(`   Cache Path: ${info.cacheFiles[0]?.path}`);
-        }
-        else {
-            const cachedFiles = info.cacheFiles.filter((f) => f.isCached).length;
-            console.log(`     Cached: ${cachedFiles}/${info.cacheFiles.length}`);
-        }
-        console.log(`   Actual Size: ${(info.actualSize / 1024 / 1024).toFixed(2)} MB`);
-        console.log(`   Cached At: ${info.cachedAt?.toLocaleString()}`);
-    }
-    if (info.loadedInstances && info.loadedInstances.length > 0) {
-        console.log(`   Loaded Instances: ${info.loadedInstances.length}`);
-        info.loadedInstances.forEach((instance, i) => {
-            console.log(`     ${i + 1}. Registry ID: ${instance.registryId}`);
-            console.log(`        Loaded At: ${instance.loadedAt.toLocaleString()}`);
-        });
-    }
-};
-try {
-    console.log("=== Model Cache Management Demo ===");
-    // 1. Check initial status
-    console.log("\n1️⃣  INITIAL STATUS CHECK");
-    const initialInfo = await getModelInfo(WHISPER_TINY);
-    printModelStatus(initialInfo, "Initial Status:");
-    // 2. Download if not cached
-    if (!initialInfo.isCached) {
-        console.log("\n2️⃣  DOWNLOADING MODEL (not cached)");
-        console.log("   Downloading from hyperdrive...");
-        await downloadAsset({ assetSrc: WHISPER_TINY });
-        console.log("   ✅ Download complete!");
-        const afterDownload = await getModelInfo(WHISPER_TINY);
-        printModelStatus(afterDownload, "Status After Download:");
-    }
-    else {
-        console.log("\n2️⃣  MODEL ALREADY CACHED");
-        console.log("   Skipping download...");
-    }
-    // 3. Load if not loaded
-    console.log("\n3️⃣  LOADING MODEL INTO MEMORY");
-    const beforeLoad = await getModelInfo(WHISPER_TINY);
-    let modelId;
-    if (!beforeLoad.isLoaded) {
-        console.log("   Loading model into memory...");
-        modelId = await loadModel({
-            modelSrc: WHISPER_TINY,
-            modelType: "whisper",
-        });
-        console.log(`   ✅ Model loaded! ID: ${modelId}`);
-        const afterLoad = await getModelInfo(WHISPER_TINY);
-        printModelStatus(afterLoad, "Status After Load:");
-    }
-    else {
-        console.log("   Model already loaded!");
-        const instances = beforeLoad.loadedInstances;
-        if (!instances || instances.length === 0) {
-            throw new Error("Model is loaded but no instances found");
-        }
-        const firstInstance = instances[0];
-        if (!firstInstance) {
-            throw new Error("First instance is undefined");
-        }
-        modelId = firstInstance.registryId;
-        console.log(`   Using existing model ID: ${modelId}`);
-    }
-    // 4. Demonstrate unload
-    console.log("\n4️⃣  UNLOADING MODEL");
-    console.log("   Unloading model from memory...");
-    await unloadModel({ modelId });
-    console.log("   ✅ Model unloaded!");
-    const afterUnload = await getModelInfo(WHISPER_TINY);
-    printModelStatus(afterUnload, "Status After Unload:");
-    // 5. Summary
-    console.log("\n5️⃣  SUMMARY");
-    console.log("   ✅ Model Info API works correctly");
-    console.log("   ✅ Cache status tracked accurately");
-    console.log("   ✅ Loaded status reflects memory state");
-    console.log("   ✅ All operations completed successfully");
-    console.log("\n=== Demo Complete ===\n");
-    process.exit(0);
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/config/blind-relay/blind-relay.config.d.ts

@@ -1,5 +0,0 @@
-declare const _default: {
-    swarmRelays: string[];
-};
-export default _default;
-//# sourceMappingURL=blind-relay.config.d.ts.map

package/dist/examples/config/blind-relay/blind-relay.config.js

@@ -1,7 +0,0 @@
-export default {
-    swarmRelays: [
-        "0000000000000000000000000000000000000000000000000000000000000001",
-        "0000000000000000000000000000000000000000000000000000000000000002",
-        "0000000000000000000000000000000000000000000000000000000000000003",
-    ],
-};

package/dist/examples/config/default/default.config.d.ts

@@ -1,8 +0,0 @@
-declare const _default: {
-    loggerLevel: string;
-    loggerConsoleOutput: boolean;
-    httpDownloadConcurrency: number;
-    httpConnectionTimeoutMs: number;
-};
-export default _default;
-//# sourceMappingURL=default.config.d.ts.map

package/dist/examples/config/default/default.config.js

@@ -1,6 +0,0 @@
-export default {
-    loggerLevel: "info",
-    loggerConsoleOutput: true,
-    httpDownloadConcurrency: 3,
-    httpConnectionTimeoutMs: 10000,
-};

package/dist/examples/config/plugins/plugins.config.d.ts

@@ -1,5 +0,0 @@
-declare const _default: {
-    plugins: ("@qvac/sdk/llamacpp-completion/plugin" | "@qvac/sdk/nmtcpp-translation/plugin")[];
-};
-export default _default;
-//# sourceMappingURL=plugins.config.d.ts.map

package/dist/examples/config/plugins/plugins.config.js

@@ -1,4 +0,0 @@
-import { PLUGIN_LLM, PLUGIN_NMT } from "@qvac/sdk";
-export default {
-    plugins: [PLUGIN_LLM, PLUGIN_NMT],
-};

package/dist/examples/config-reload.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=config-reload.d.ts.map

package/dist/examples/config-reload.js

@@ -1,49 +0,0 @@
-import { WHISPER_TINY, loadModel, transcribe, unloadModel } from "../index";
-// Parse command line arguments
-const args = process.argv.slice(2);
-if (!args[0]) {
-    console.error("Usage: bun run examples/config-reload.ts <audio-file-path>");
-    process.exit(1);
-}
-const audioFilePath = args[0];
-try {
-    // Initial load with English language
-    console.log("Loading Whisper model with English config...");
-    const modelId = await loadModel({
-        modelSrc: WHISPER_TINY,
-        modelType: "whisper",
-        modelConfig: {
-            language: "en",
-        },
-    });
-    // Transcribe with English config
-    console.log("Transcribing audio with English config...");
-    const englishText = await transcribe({
-        modelId,
-        audioChunk: audioFilePath,
-    });
-    console.log(`Transcription (EN): ${englishText}`);
-    console.log();
-    // Hot reload config - change language and temperature
-    console.log("Hot reloading config (changing language and temperature)...");
-    const reloadedId = await loadModel({
-        modelId,
-        modelType: "whisper",
-        modelConfig: {
-            language: "es", // Change to Spanish
-        },
-    });
-    console.log(`Config reloaded, same model ID: ${reloadedId === modelId}`);
-    // Transcribe again with updated config
-    console.log("Transcribing with updated config...");
-    const spanishText = await transcribe({
-        modelId,
-        audioChunk: audioFilePath,
-    });
-    console.log(`Transcription (ES): ${spanishText}`);
-    await unloadModel({ modelId });
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/default-config-usage.d.ts

@@ -1,17 +0,0 @@
-/**
- * Default Config Example
- *
- * This example demonstrates how to use a config file with the SDK.
- *
- * Supported config formats:
- * - qvac.config.json (JSON)
- * - qvac.config.js   (JavaScript with default export)
- * - qvac.config.ts   (TypeScript with default export)
- *
- * Config resolution order:
- * 1. QVAC_CONFIG_PATH environment variable (used here for demo purposes)
- * 2. Config file in project root - auto-discovered, no env var needed
- * 3. SDK defaults
- */
-export {};
-//# sourceMappingURL=default-config-usage.d.ts.map

package/dist/examples/default-config-usage.js

@@ -1,47 +0,0 @@
-/**
- * Default Config Example
- *
- * This example demonstrates how to use a config file with the SDK.
- *
- * Supported config formats:
- * - qvac.config.json (JSON)
- * - qvac.config.js   (JavaScript with default export)
- * - qvac.config.ts   (TypeScript with default export)
- *
- * Config resolution order:
- * 1. QVAC_CONFIG_PATH environment variable (used here for demo purposes)
- * 2. Config file in project root - auto-discovered, no env var needed
- * 3. SDK defaults
- */
-// Note: This example uses .js file for the config
-// However it could be .json or .ts as well, depending on your needs.
-const configDir = import.meta.dirname ?? process.cwd();
-process.env["QVAC_CONFIG_PATH"] =
-    `${configDir}/config/default/default.config.js`;
-console.log(`🔍 Using config from: ${process.env["QVAC_CONFIG_PATH"]}`);
-const { loadModel, unloadModel, completion, LLAMA_3_2_1B_INST_Q4_0 } = await import("@qvac/sdk");
-try {
-    console.log("🚀 Loading model with configured settings...\n");
-    const modelId = await loadModel({
-        modelSrc: LLAMA_3_2_1B_INST_Q4_0,
-        modelType: "llm",
-    });
-    console.log("\n💬 Running completion...\n");
-    const result = completion({
-        modelId,
-        history: [
-            { role: "user", content: "Say 'Config works!' in exactly 3 words." },
-        ],
-        stream: true,
-    });
-    for await (const token of result.tokenStream) {
-        process.stdout.write(token);
-    }
-    console.log("\n");
-    await unloadModel({ modelId });
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}
-export {};

package/dist/examples/delegated-inference/consumer-profiled.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=consumer-profiled.d.ts.map

package/dist/examples/delegated-inference/consumer-profiled.js

@@ -1,67 +0,0 @@
-import { close, completion, LLAMA_3_2_1B_INST_Q4_0, loadModel, profiler, } from "@qvac/sdk";
-const topicHex = process.argv[2];
-if (!topicHex) {
-    console.error("❌ Usage: bun run consumer-profiled.ts <topic> <publicKey>");
-    process.exit(1);
-}
-const providerPublicKey = process.argv[3];
-if (!providerPublicKey) {
-    console.error("❌ Usage: bun run consumer-profiled.ts <topic> <publicKey>");
-    process.exit(1);
-}
-try {
-    profiler.enable({ mode: "verbose", includeServerBreakdown: true });
-    console.log("✓ Profiler enabled");
-    console.log(`\n📡 Topic: ${topicHex}`);
-    console.log(`🔑 Provider: ${providerPublicKey}\n`);
-    console.log("→ Loading model (delegated, unary)...");
-    const modelId = await loadModel({
-        modelSrc: LLAMA_3_2_1B_INST_Q4_0,
-        modelType: "llm",
-        delegate: {
-            topic: topicHex,
-            providerPublicKey,
-            timeout: 30_000,
-        },
-    });
-    console.log(`✓ Model loaded: ${modelId}\n`);
-    console.log("→ Running completion (delegated, streamed)...");
-    const response = completion({
-        modelId,
-        history: [{ role: "user", content: "Say hello in exactly 5 words." }],
-        stream: true,
-    });
-    process.stdout.write("  Response: ");
-    for await (const token of response.tokenStream) {
-        process.stdout.write(token);
-    }
-    await response.stats;
-    console.log("\n✓ Completion done\n");
-    console.log("=== Profiler Summary ===");
-    console.log(profiler.exportSummary());
-    console.log("=== Profiler Table ===");
-    console.log(profiler.exportTable());
-    // Look for delegation-specific metrics
-    const json = profiler.exportJSON();
-    const delegationMetrics = Object.keys(json.aggregates).filter((k) => k.includes("delegation") || k.includes("delegated"));
-    if (delegationMetrics.length > 0) {
-        console.log("=== Delegation Metrics ===");
-        for (const key of delegationMetrics) {
-            const agg = json.aggregates[key];
-            if (agg) {
-                console.log(`  ${key}: ${agg.avg.toFixed(2)}ms (count: ${agg.count})`);
-            }
-        }
-    }
-    else {
-        console.log("⚠️  No delegation-specific metrics found");
-        console.log("    (delegation profiling may need to be triggered)");
-    }
-    profiler.disable();
-    void close();
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    profiler.disable();
-    process.exit(1);
-}

package/dist/examples/download-with-blind-relays.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=download-with-blind-relays.d.ts.map

package/dist/examples/download-with-blind-relays.js

@@ -1,49 +0,0 @@
-// Set config path before importing SDK - the SDK loads config during initialization
-// This example uses a config file that defines blind relay public keys for improved P2P connectivity
-// Blind relays help establish connections through NAT/firewalls by acting as intermediaries
-const configDir = import.meta.dirname ?? process.cwd();
-process.env["QVAC_CONFIG_PATH"] =
-    `${configDir}/config/blind-relay/blind-relay.config.js`;
-import { downloadAsset, close, LLAMA_3_2_1B_INST_Q4_0, loadModel, getModelInfo, unloadModel, } from "@qvac/sdk";
-console.log(`🚀 Download with Blind Relays Example`);
-console.log(`${"=".repeat(60)}\n`);
-try {
-    // Config is loaded from examples/config/qvac.config.json (set via QVAC_CONFIG_PATH above)
-    // The config contains swarmRelays - an array of Hyperswarm relay public keys
-    // These relays help with NAT traversal and firewall bypassing for P2P downloads
-    console.log(`📥 Starting model download from Hyperdrive...\n`);
-    const startTime = Date.now();
-    const modelId = await loadModel({
-        modelSrc: LLAMA_3_2_1B_INST_Q4_0,
-        modelType: "llm",
-    });
-    console.log(`Model loaded with ID: ${modelId}`);
-    const firstStatus = await getModelInfo(LLAMA_3_2_1B_INST_Q4_0);
-    console.log(`First status: ${JSON.stringify(firstStatus)}`);
-    await unloadModel({ modelId });
-    // Download model with progress tracking
-    await downloadAsset({
-        assetSrc: LLAMA_3_2_1B_INST_Q4_0,
-        onProgress: (progress) => {
-            const downloadedMB = (progress.downloaded / 1024 / 1024).toFixed(2);
-            const totalMB = (progress.total / 1024 / 1024).toFixed(2);
-            const percentage = progress.percentage.toFixed(1);
-            const elapsedSeconds = (Date.now() - startTime) / 1000;
-            const speedMBps = (progress.downloaded /
-                1024 /
-                1024 /
-                elapsedSeconds).toFixed(2);
-            console.log(`📊 ${percentage}% - ${downloadedMB}MB / ${totalMB}MB (${speedMBps} MB/s)`);
-        },
-    });
-    console.log(`\n✅ Model downloaded successfully using blind relays!`);
-    console.log(`Blind relays helped establish peer connections through NAT/firewalls\n`);
-    await close();
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    console.log(`\nIf download failed, check the relay public keys in:`);
-    console.log(`   examples/config/qvac.config.json`);
-    console.log(`   (Mock keys in this example won't work in practice!)`);
-    process.exit(1);
-}

package/dist/examples/llamacpp-sharded.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=llamacpp-sharded.d.ts.map

package/dist/examples/llamacpp-sharded.js

@@ -1,53 +0,0 @@
-import { completion, loadModel, unloadModel, VERBOSITY } from "@qvac/sdk";
-// Sharded models can be loaded from:
-// 1. HTTP archives: "https://example.com/model.tar.gz"
-// 2. HTTP pattern: "https://example.com/model-00001-of-00005.gguf"
-// 3. Hyperdrive: use any sharded model source/constant, eg: LLAMA_3_2_1B_INST_Q4_0_SHARD
-// 4. Local filesystem: pass the path to the first shard file (Note: All shards must be in the same directory)
-// 5. Local archive: pass the path to the archive file (.tar, .tar.gz, .tgz)
-try {
-    const modelId = await loadModel({
-        modelSrc: "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct-GGUF/resolve/main/qwen2.5-coder-7b-instruct-q4_0-00001-of-00002.gguf",
-        modelType: "llm",
-        modelConfig: {
-            device: "gpu",
-            ctx_size: 2048,
-            verbosity: VERBOSITY.ERROR,
-        },
-        onProgress: (progress) => {
-            // For sharded models, progress.shardInfo contains detailed progress for both
-            // individual shards AND overall download progress across all shards
-            if (progress.shardInfo) {
-                // For pattern-based or Hyperdrive shards
-                const { shardInfo } = progress;
-                console.log(`📥 Downloading ${shardInfo.shardName} (${shardInfo.currentShard}/${shardInfo.totalShards})\n` +
-                    `   File: ${progress.percentage.toFixed(1)}% (${(progress.downloaded / 1024 / 1024).toFixed(2)}MB / ${(progress.total / 1024 / 1024).toFixed(2)}MB)\n` +
-                    `   Overall: ${shardInfo.overallPercentage.toFixed(1)}% (${(shardInfo.overallDownloaded / 1024 / 1024).toFixed(2)}MB / ${(shardInfo.overallTotal / 1024 / 1024).toFixed(2)}MB)`);
-            }
-            else {
-                // For archive-based shards
-                console.log(`📥 Progress: ${progress.percentage.toFixed(1)}% ` +
-                    `(${(progress.downloaded / 1024 / 1024).toFixed(2)}MB / ${(progress.total / 1024 / 1024).toFixed(2)}MB)`);
-            }
-        },
-    });
-    const history = [
-        {
-            role: "user",
-            content: "What are the benefits of sharding large language models? Use emojis in your response.",
-        },
-    ];
-    const result = completion({ modelId, history, stream: true });
-    console.log("\n🤖 Model response:");
-    for await (const token of result.tokenStream) {
-        process.stdout.write(token);
-    }
-    const stats = await result.stats;
-    console.log("\n\n📊 Performance Stats:", stats);
-    await unloadModel({ modelId, clearStorage: false });
-    process.exit(0);
-}
-catch (error) {
-    console.error("❌ Error:", error);
-    process.exit(1);
-}

package/dist/examples/logging-file-transport.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=logging-file-transport.d.ts.map

package/dist/examples/logging-streaming.d.ts

@@ -1,2 +0,0 @@
-export {};
-//# sourceMappingURL=logging-streaming.d.ts.map