v2: add embedding tests, multilingual embedding support

Tests/01_Model/EmbeddingTest.swift

@@ -0,0 +1,80 @@
+import XCTest
+@testable import MarkBase
+
+final class EmbeddingTest: XCTestCase {
+    var engine: MarkBaseEngine!
+    var model: E4BModel!
+    var embeddingModel: TextEmbeddingModel!
+    let modelDir = "/Users/accusys/MarkBaseEngine/models/E4B-MarkBase"
+
+    override func setUp() {
+        super.setUp()
+        guard FileManager.default.fileExists(atPath: modelDir + "/model.safetensors") else {
+            return
+        }
+        engine = try? MarkBaseEngine(autoCompile: true)
+        model = try? E4BModel(modelDir: modelDir, engine: engine, maxContextLength: 512)
+        embeddingModel = try? TextEmbeddingModel(modelDir: modelDir, engine: engine, config: TextEmbeddingConfig())
+    }
+
+    func testEmbeddingDimension() throws {
+        try XCTSkipIf(embeddingModel == nil, "Model not found")
+        let embedding = try embeddingModel.embed(text: "Hello world")
+        XCTAssertEqual(embedding.count, 2560, "Embedding dimension should be 2560")
+    }
+
+    func testEmbeddingNormalized() throws {
+        try XCTSkipIf(embeddingModel == nil, "Model not found")
+        let embedding = try embeddingModel.embed(text: "Test text")
+        let norm = sqrt(embedding.reduce(0) { $0 + $1 * $1 })
+        XCTAssertEqual(norm, 1.0, accuracy: 0.001, "Embedding should be L2 normalized")
+    }
+
+    func testSimilarSentences() throws {
+        try XCTSkipIf(embeddingModel == nil, "Model not found")
+        let e1 = try embeddingModel.embed(text: "The cat is sitting on the mat")
+        let e2 = try embeddingModel.embed(text: "A cat rests on a rug")
+        let e3 = try embeddingModel.embed(text: "The stock market crashed today")
+
+        let sim12 = cosineSimilarity(e1, e2)
+        let sim13 = cosineSimilarity(e1, e3)
+        print("Similar(cat, cat): \(sim12)")
+        print("Similar(cat, stock): \(sim13)")
+        XCTAssertGreaterThan(sim12, sim13, "Similar sentences should have higher cosine similarity")
+    }
+
+    func testDifferentLengths() throws {
+        try XCTSkipIf(embeddingModel == nil, "Model not found")
+        let e1 = try embeddingModel.embed(text: "Hi")
+        let e2 = try embeddingModel.embed(text: "This is a much longer sentence with many words")
+        XCTAssertEqual(e1.count, e2.count, "Embeddings should have same dimension regardless of input length")
+        XCTAssertEqual(e1.count, 2560)
+    }
+
+    func testEmptyInput() throws {
+        try XCTSkipIf(embeddingModel == nil, "Model not found")
+        let embedding = try embeddingModel.embed(text: "")
+        XCTAssertEqual(embedding.count, 0, "Empty input should return empty embedding")
+    }
+
+    func testBatchEmbedding() throws {
+        try XCTSkipIf(embeddingModel == nil, "Model not found")
+        let texts = ["Hello", "World", "Test"]
+        let embeddings = try embeddingModel.embedBatch(texts: texts)
+        XCTAssertEqual(embeddings.count, 3)
+        for embedding in embeddings {
+            XCTAssertEqual(embedding.count, 2560)
+        }
+    }
+
+    private func cosineSimilarity(_ a: [Float], _ b: [Float]) -> Float {
+        guard a.count == b.count, !a.isEmpty else { return 0 }
+        var dot: Float = 0, normA: Float = 0, normB: Float = 0
+        for i in 0..<a.count {
+            dot += a[i] * b[i]
+            normA += a[i] * a[i]
+            normB += b[i] * b[i]
+        }
+        return dot / (sqrt(normA) * sqrt(normB))
+    }
+}

Tests/01_Model/MultilangEmbeddingTest.swift

@@ -0,0 +1,78 @@
+import XCTest
+@testable import MarkBase
+
+final class MultilangEmbeddingTest: XCTestCase {
+    var engine: MarkBaseEngine!
+    var embeddingModel: TextEmbeddingModel!
+    let modelDir = "/Users/accusys/MarkBaseEngine/models/E4B-MarkBase"
+
+    override func setUp() {
+        super.setUp()
+        guard FileManager.default.fileExists(atPath: modelDir + "/model.safetensors") else { return }
+        engine = try? MarkBaseEngine(autoCompile: true)
+        embeddingModel = try? TextEmbeddingModel(modelDir: modelDir, engine: engine, config: TextEmbeddingConfig())
+    }
+
+    func testMultilangEmbeddings() throws {
+        try XCTSkipIf(embeddingModel == nil, "Model not found")
+
+        let texts: [String: String] = [
+            "en": "The weather is beautiful today",
+            "zh": "今天天氣很好",
+            "ja": "今日は天気がいいです",
+            "ko": "오늘 날씨가 좋습니다",
+            "es": "El clima está hermoso hoy",
+            "fr": "Il fait beau aujourd'hui",
+            "de": "Das Wetter ist heute schön",
+            "ru": "Сегодня прекрасная погода",
+            "ar": "الطقس جميل اليوم",
+            "hi": "आज मौसम बहुत सुंदर है"
+        ]
+
+        var embeddings: [String: [Float]] = [:]
+        for (lang, text) in texts {
+            let emb = try embeddingModel.embed(text: text)
+            XCTAssertEqual(emb.count, 2560, "\(lang) embedding dimension")
+            let norm = sqrt(emb.reduce(0) { $0 + $1 * $1 })
+            XCTAssertEqual(norm, 1.0, accuracy: 0.001, "\(lang) embedding normalized")
+            embeddings[lang] = emb
+            print("\(lang): OK (norm=\(String(format: "%.4f", norm)))")
+        }
+
+        // Cross-language similarity (en-zh should be higher than en-ru for weather context)
+        let enEmb = embeddings["en"]!
+        let zhEmb = embeddings["zh"]!
+        let jaEmb = embeddings["ja"]!
+
+        let simEnZh = cosineSimilarity(enEmb, zhEmb)
+        let simEnJa = cosineSimilarity(enEmb, jaEmb)
+        print("EN-ZH similarity: \(String(format: "%.4f", simEnZh))")
+        print("EN-JA similarity: \(String(format: "%.4f", simEnJa))")
+    }
+
+    func testCrossLingualSemanticSimilarity() throws {
+        try XCTSkipIf(embeddingModel == nil, "Model not found")
+
+        // Same meaning, different languages
+        let enCat = try embeddingModel.embed(text: "The cat is sleeping")
+        let zhCat = try embeddingModel.embed(text: "貓在睡覺")
+        let enDog = try embeddingModel.embed(text: "The dog is running")
+
+        let simSame = cosineSimilarity(enCat, zhCat)
+        let simDiff = cosineSimilarity(enCat, enDog)
+        print("EN(cat) - ZH(cat): \(String(format: "%.4f", simSame))")
+        print("EN(cat) - EN(dog): \(String(format: "%.4f", simDiff))")
+        print("Cross-lingual > Same-lingual different topic: \(simSame > simDiff)")
+    }
+
+    private func cosineSimilarity(_ a: [Float], _ b: [Float]) -> Float {
+        guard a.count == b.count, !a.isEmpty else { return 0 }
+        var dot: Float = 0, normA: Float = 0, normB: Float = 0
+        for i in 0..<a.count {
+            dot += a[i] * b[i]
+            normA += a[i] * a[i]
+            normB += b[i] * b[i]
+        }
+        return dot / (sqrt(normA) * sqrt(normB))
+    }
+}

Tests/01_Model/Timing26BTest.swift

@@ -0,0 +1,33 @@
+import Foundation
+import XCTest
+
+@testable import MarkBase
+
+final class Timing26BTest: XCTestCase {
+    let modelDir = "/Users/accusys/MarkBaseEngine/models/gemma-4-26b-standard"
+    var engine: MarkBaseEngine!
+    var model: E4BModel!
+    let maxCtx = 128
+
+    override func setUp() {
+        super.setUp()
+        guard FileManager.default.fileExists(atPath: modelDir + "/model.safetensors") else {
+            return
+        }
+        let t0 = Date()
+        engine = try? MarkBaseEngine(autoCompile: true)
+        model = try? E4BModel(modelDir: modelDir, engine: engine, maxContextLength: maxCtx)
+        let loadTime = Date().timeIntervalSince(t0)
+        print("Total init: \(String(format: "%.1f", loadTime))s")
+    }
+
+    func testForwardTiming() throws {
+        try XCTSkipIf(model == nil, "26B model not found")
+        for i in 0..<5 {
+            let t = Date()
+            _ = try model.forward(tokenId: 100 + i, position: i)
+            let ft = Date().timeIntervalSince(t)
+            print("Forward \(i+1): \(String(format: "%.3f", ft))s")
+        }
+    }
+}