forked from masonhuang/cluster4npu
abin
55040733fe
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>
33 lines
874 B
Python
33 lines
874 B
Python
"""
|
|
core/device/bottleneck.py
|
|
|
|
BottleneckAlert dataclass — describes a detected pipeline bottleneck.
|
|
|
|
Integration with InferencePipeline is deferred to a later phase.
|
|
This module only defines the data structure.
|
|
"""
|
|
from dataclasses import dataclass
|
|
|
|
|
|
@dataclass
|
|
class BottleneckAlert:
|
|
"""Describes a detected pipeline bottleneck in a single Stage.
|
|
|
|
Attributes
|
|
----------
|
|
stage_id:
|
|
The pipeline Stage that is experiencing the bottleneck.
|
|
queue_fill_rate:
|
|
Input queue utilisation as a fraction in [0.0, 1.0].
|
|
suggested_action:
|
|
Human-readable suggestion (e.g. "Add more Dongles to this stage").
|
|
severity:
|
|
Either ``"warning"`` (fill_rate > 0.8) or ``"critical"``
|
|
(fill_rate > 0.95).
|
|
"""
|
|
|
|
stage_id: str
|
|
queue_fill_rate: float
|
|
suggested_action: str
|
|
severity: str # "warning" | "critical"
|