// Minimal test: only forward pass, no token generation import Foundation @testable import MarkBase let modelPath = "/Users/accusys/MarkBaseEngine/models/gemma-4-26b-a4b-it-4bit" print("=====================================") print("26B-A4B MoE Forward Pass Test ONLY") print("=====================================") print("\n[1] Loading model...") let start1 = Date() let engine = try E4BEngine(autoCompile: true) print("✓ Engine created") let model = try E4BModel(modelDir: modelPath, engine: engine, maxContextLength: 128) let loadTime = Date().timeIntervalSince(start1) print("✓ Model loaded in \(String(format: "%.3f", loadTime))s") print("\n[2] Testing single forward pass...") let tokenizer = try TokenizerFactory.load(modelDir: modelPath) let prompt = "Hello" let tokens = tokenizer.encode(text: prompt) print(" Prompt: \"\(prompt)\" -> tokens: \(tokens)") // Create input buffer let embed = model.embedTokens let inputBuffer = engine.createBuffer(length: model.hiddenSize * 4) let outputBuffer = engine.createBuffer(length: model.vocabSize * 4) // Get embedding for first token let embedData = engine.readFloats(from: embed.weight, offset: tokens[0] * model.hiddenSize, count: model.hiddenSize) engine.writeFloats(embedData, to: inputBuffer) print(" Input buffer: \(model.hiddenSize) floats") print(" Running forward pass through \(model.numHiddenLayers) layers...") let start2 = Date() // Run through all layers for i in 0..