From 7e686c3c5a33f1df6f111cdc7a258e5b67614799 Mon Sep 17 00:00:00 2001
From: MarkBase Admin <admin@markbase.local>
Date: Mon, 6 Jul 2026 01:01:43 +0800
Subject: [PATCH] v2: add long context 12B test (256 tokens)

---
 Tests/01_Model/LongContext12BTest.swift | 56 +++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 Tests/01_Model/LongContext12BTest.swift

diff --git a/Tests/01_Model/LongContext12BTest.swift b/Tests/01_Model/LongContext12BTest.swift
new file mode 100644
index 0000000..4d47e78
--- /dev/null
+++ b/Tests/01_Model/LongContext12BTest.swift
@@ -0,0 +1,56 @@
+import XCTest
+@testable import MarkBase
+
+final class LongContext12BTest: XCTestCase {
+
+    var engine: MarkBaseEngine!
+    var model: E4BModel!
+    let modelDir = "/Users/accusys/MarkBaseEngine/models/gemma-4-12b-it-4bit"
+    let maxCtx = 2048
+
+    override func setUp() {
+        super.setUp()
+        guard FileManager.default.fileExists(atPath: modelDir + "/model.safetensors.index.json") else {
+            return
+        }
+        engine = try? MarkBaseEngine(autoCompile: true)
+        model = try? E4BModel(modelDir: modelDir, engine: engine, maxContextLength: maxCtx)
+    }
+
+    func testLongContext256Tokens() throws {
+        try XCTSkipIf(model == nil, "12B model not found")
+
+        let promptLength = 256
+        var tokens = [Int]()
+        for i in 0..<promptLength {
+            tokens.append(100 + (i % 1000))
+        }
+
+        for (pos, tokenId) in tokens.enumerated() {
+            let logits = try model.forward(tokenId: tokenId, position: pos)
+            if pos == 0 || pos == promptLength - 1 {
+                let nanCount = logits.filter { $0.isNaN }.count
+                XCTAssertEqual(nanCount, 0, "NaN at pos=\(pos)")
+            }
+            if pos % 64 == 0 {
+                let sample = logits.prefix(5)
+                let nanCount = logits.filter { $0.isNaN }.count
+                print("  pos=\(pos): logits[0..5]=\(sample) NaN=\(nanCount)")
+            }
+        }
+
+        var genTokens = tokens
+        for i in 0..<5 {
+            let logits = try model.forward(tokenId: genTokens.last ?? 0, position: genTokens.count - 1)
+            let nanCount = logits.filter { $0.isNaN }.count
+            XCTAssertEqual(nanCount, 0, "NaN at gen step \(i)")
+            var maxIdx = 0
+            var maxVal = logits[0]
+            for j in 1..<logits.count {
+                if logits[j] > maxVal { maxVal = logits[j]; maxIdx = j }
+            }
+            genTokens.append(maxIdx)
+            print("  gen[\(i)]: token=\(maxIdx) logit=\(maxVal)")
+        }
+    }
+}