MarkBase Admin
ac75faa0cc
CI / build-and-test (push) Has been cancelled
- E4B-MarkBase model (42 layers, 4.4GB) loaded successfully - All Phase 1-6 tests passed (model loading, forward pass, vision/audio towers, token generation, performance) - All stress tests passed (5/5 in 127.6s) - Concurrent inference - Memory stress (67.5 tok/s, 0 NaN) - Continuous generation - Batch processing - Long-running stability - Swift Metal inference engine with multimodal support
32 lines
1.3 KiB
Swift
32 lines
1.3 KiB
Swift
import MarkBase
|
|
|
|
/// Entry point for MarkBase API server
|
|
/// Usage: swift run G12BServer [model_dir] [port] [model_id] [--benchmark]
|
|
@main
|
|
public struct ServerMain {
|
|
public static func main() async throws {
|
|
let args = CommandLine.arguments
|
|
|
|
// Check for benchmark mode
|
|
if args.contains("--benchmark") {
|
|
let modelDir = args.count > 2 ? args[1] : "./model"
|
|
let modelName = args.count > 3 ? args[2] : "markbase"
|
|
|
|
var benchmark = PerformanceBenchmark(modelDir: modelDir, modelName: modelName)
|
|
try await benchmark.run()
|
|
return
|
|
}
|
|
|
|
let modelDir = args.count > 1 ? args[1] : "./model"
|
|
let port = args.count > 2 ? Int(args[2]) ?? 8080 : 8080
|
|
let modelId = args.count > 3 ? args[3] : "markbase-12b"
|
|
|
|
print("\n╔═════════════════════════════════════════════╗")
|
|
print("║ MarkBase API Server ║")
|
|
print("╚═════════════════════════════════════════════╝\n")
|
|
|
|
let server = try MarkBaseServer(modelDir: modelDir, modelId: modelId)
|
|
try await server.start(port: port)
|
|
}
|
|
}
|