forked from masonhuang/cluster4npu
Phase 1 — Performance Benchmarking: - PerformanceBenchmarker: sequential vs parallel benchmark with injectable runner - PerformanceHistory: JSON-backed benchmark history with regression support - PerformanceDashboard: real-time FPS/latency display widget - BenchmarkDialog: one-click benchmark with 3-phase progress bar Phase 2 — Device Management: - DeviceManager: NPU dongle scan, assign/unassign, load balance recommendation - DeviceManagementPanel: live device status cards with auto-refresh - BottleneckAlert: dataclass for pipeline bottleneck detection Phase 3 — Advanced Features: - OptimizationEngine: 3 optimization rules (rebalance/adjust_queue/add_devices) - TemplateManager: 3 built-in pipeline templates (YOLOv5, fire detection, dual-model) Phase 4 — Report Export: - ReportExporter: PDF (reportlab, optional) and CSV export - ExportReportDialog: format selection + path picker UI 192 unit tests, all passing. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2 lines
59 B
Python
2 lines
59 B
Python
"""core/optimization — Pipeline 優化建議模組。"""
|