Edit photos by describing the change, on your own GPU. A free, open-source alternative to Nano Banana and ChatGPT image editing: photos stay on your computer, no daily limit. One installer for Windows, Mac and Linux sets up the best open model (Qwen-Image 2.1). MCP server for AI agents.
TypeScript ai-photo-editorcomfyui-alternativegenerative-fillimage-editingimage-generationinpaintinglinuxlocal-aimacosmcpmcp-servernano-banana-alternativeofflinephoto-editorprivacyqwen-imageqwen-image-2-1stable-diffusion-cppvulkanwindows
import XCTest
@testable import KokonEngine
/// Text generation's sampler, which must draw what sd.cpp's draws for a seed (`src/runtime/text_sampler.cpp`).
final class TextGenerationTests: XCTestCase {
/// The C++ standard fixes mt19937_64's output: the 10 000th number from the default seed 5489.
func testMersenneTwisterIsTheStandards() {
var random = MersenneTwister64(seed: 5489)
XCTAssertEqual(random.next(), 14_514_284_786_278_117_030)
for _ in 2..<10_000 { _ = random.next() }
XCTAssertEqual(random.next(), 9_981_545_732_273_789_042)
}
func testGreedyTakesTheLowestIDOnTiesAndPenalizesSeenTokens() {
var sampler = TextSampler(TextSampler.Parameters(temperature: 0, topP: 1, topK: 0, presencePenalty: 1.5), seed: 1)
let logits: [Float] = [1, 3, 3, 2]
XCTAssertEqual(logits.withUnsafeBufferPointer { sampler.sample($0.baseAddress!, count: 4) }, 1)
// 1 was generated: 3 − 1.5 < 3, so 2 wins.
XCTAssertEqual(logits.withUnsafeBufferPointer { sampler.sample($0.baseAddress!, count: 4) }, 2)
// Both penalized to 1.5: 3 (logit 2) wins.
XCTAssertEqual(logits.withUnsafeBufferPointer { sampler.sample($0.baseAddress!, count: 4) }, 3)
}
func testCandidatesTopKTemperatureTopP() {
let sampler = TextSampler(TextSampler.Parameters(temperature: 0.5, topP: 0.8, topK: 3, presencePenalty: 0), seed: 1)
let logits: [Float] = [0, 2, 1, 2, -1]
let c = logits.withUnsafeBufferPointer { sampler.candidates($0.baseAddress!, count: 5) }
// Top 3 by logit (ties by id): 1, 3, 2; at T 0.5 their weights are 1, 1, e^-2; 1 + 1 reach 0.8 of the sum.
XCTAssertEqual(c.map(\.token), [1, 3])
XCTAssertEqual(c[0].p, 0.5, accuracy: 1e-12)
let all = TextSampler(TextSampler.Parameters(temperature: 1, topP: 1, topK: 0, presencePenalty: 0), seed: 1)
let p = logits.withUnsafeBufferPointer { all.candidates($0.baseAddress!, count: 5) }
XCTAssertEqual(p.map(\.token), [1, 3, 2, 0, 4])
XCTAssertEqual(p.reduce(0) { $0 + $1.p }, 1, accuracy: 1e-12)
XCTAssertEqual(p[2].p / p[0].p, exp(-1), accuracy: 1e-12)
}
/// A draw is the first candidate whose cumulative probability passes a uniform double of 53 bits from the seed.
func testDrawFollowsTheSeed() {
let parameters = TextSampler.Parameters(temperature: 1, topP: 1, topK: 0, presencePenalty: 0)
let logits: [Float] = [0, 0] // 0.5 each: token 0 when u < 0.5
for seed: UInt64 in [1, 2, 3, 42] {
var sampler = TextSampler(parameters, seed: seed)
var random = MersenneTwister64(seed: seed)
let u = Double(random.next() >> 11) / 9_007_199_254_740_992.0
XCTAssertEqual(logits.withUnsafeBufferPointer { sampler.sample($0.baseAddress!, count: 2) }, u < 0.5 ? 0 : 1)
}
}
func testTemplateIsSdcpps() {
XCTAssertEqual(QwenTextGenerator.template(system: "S", prompt: "P"),
"<|im_start|>system\nS<|im_end|>\n<|im_start|>user\nP<|im_end|>\n<|im_start|>assistant\n")
XCTAssertEqual(QwenTextGenerator.template(system: "", prompt: "P"), "<|im_start|>user\nP<|im_end|>\n<|im_start|>assistant\n")
}
}
/// The decode's matrix-vector products on Q4_K and Q6_K blocks against the CPU's unpacking (`Dequant.row`) and a dot
/// product in double: random blocks with sane scales, 3 blocks a row (ragged across the SIMD group's lanes).
final class MatvecKernelTests: XCTestCase {
func testMatvecMatchesTheUnpackedRows() throws {
let context = try MetalContext()
var s: UInt64 = 7
func next() -> UInt64 { s = s &* 6364136223846793005 &+ 1442695040888963407; return s >> 33 }
for (type, kernel) in [(QuantType.q4_K, "matvec_q4_K"), (.q6_K, "matvec_q6_K")] {
let rows = 37, columns = 3 * 256, rowBytes = type.bytes(count: columns)
var bytes = (0..<(rows * rowBytes)).map { _ in UInt8(truncatingIfNeeded: next()) }
// The fp16 scales of every block: small positive values (random bytes may be NaN or huge).
for r in 0..<rows {
for b in 0..<3 {
let block = r * rowBytes + b * type.blockBytes
let scaleOffsets = type == .q4_K ? [0, 2] : [208]
for o in scaleOffsets {
let v = Float16(Float(next() % 1000 + 1) * 1e-5)
withUnsafeBytes(of: v.bitPattern.littleEndian) { bytes[block + o] = $0[0]; bytes[block + o + 1] = $0[1] }
}
}
}
let x = (0..<columns).map { _ in Float(Int(next() % 2001) - 1000) / 500 }
let w = try context.scratch(bytes.count, label: "w"), xb = try context.scratch(columns * 4, label: "x"), y = try context.scratch(rows * 4, label: "y")
w.contents().copyMemory(from: bytes, byteCount: bytes.count)
xb.contents().copyMemory(from: x, byteCount: columns * 4)
let commands = context.queue.makeCommandBuffer()!
let e = commands.makeComputeCommandEncoder()!
e.setComputePipelineState(try context.pipeline(kernel))
e.setBuffer(w, offset: 0, index: 0); e.setBuffer(xb, offset: 0, index: 1); e.setBuffer(y, offset: 0, index: 2)
var params = QwenTextGenerator.MatvecParams(rows: UInt32(rows), blocksPerRow: 3, rowBytes: UInt32(rowBytes))
e.setBytes(¶ms, length: MemoryLayout<QwenTextGenerator.MatvecParams>.stride, index: 3)
let perGroup = QwenTextGenerator.matvecRows(type)
e.dispatchThreadgroups(MTLSize(width: (rows + perGroup - 1) / perGroup, height: 1, depth: 1), threadsPerThreadgroup: MTLSize(width: 128, height: 1, depth: 1))
e.endEncoding()
try MetalContext.finish(commands, kernel)
let got = y.contents().assumingMemoryBound(to: Float.self)
var unpacked = [Float](repeating: 0, count: columns)
for r in 0..<rows {
bytes.withUnsafeBytes { Dequant.row($0.baseAddress! + r * rowBytes, type: type, count: columns, into: &unpacked) }
let want = zip(unpacked, x).reduce(0.0) { $0 + Double($1.0) * Double($1.1) }
let scale = zip(unpacked, x).reduce(0.0) { $0 + abs(Double($1.0) * Double($1.1)) }
XCTAssertEqual(Double(got[r]), want, accuracy: 1e-5 * scale + 1e-9, "\(kernel) row \(r)")
}
}
}
}