mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-03-09 15:23:00 -05:00
a78f1bd8b0
Complete MLSYSIM v0.1.0 implementation with: - Documentation website (Quarto): landing page with animated hero and capability carousel, 4 tutorials (hello world, LLM serving, distributed training, sustainability), hardware/model/fleet/infra catalogs, solver guide, whitepaper, math foundations, glossary, and full quartodoc API reference - Typed registry system: Hardware (18 devices across 5 tiers), Models (15 workloads), Systems (fleets, clusters, fabrics), Infrastructure (grid profiles, rack configs, datacenters) - Core types: Pint-backed Quantity, Metadata provenance tracking, custom exception hierarchy (OOMError, SLAViolation) - SimulationConfig with YAML/JSON loading and pre-validation - Scenario system tying workloads to systems with SLA constraints - Multi-level evaluation scorecard (feasibility, performance, macro) - Examples, tests, and Jetson Orin NX spec fix (100 → 25 TFLOP/s) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
21 lines
723 B
Python
21 lines
723 B
Python
# Exceptions for the MLSys Simulator
|
|
|
|
class MLSysError(Exception):
|
|
"""Base exception for all mlsysim simulation errors."""
|
|
pass
|
|
|
|
class OOMError(MLSysError):
|
|
"""Raised when a workload's memory footprint exceeds the hardware capacity."""
|
|
def __init__(self, message, required_bytes=None, available_bytes=None):
|
|
super().__init__(message)
|
|
self.required_bytes = required_bytes
|
|
self.available_bytes = available_bytes
|
|
|
|
class ThermalThrottleWarning(UserWarning):
|
|
"""Warning for when continuous utilization might cause thermal downclocking."""
|
|
pass
|
|
|
|
class SLAViolation(MLSysError):
|
|
"""Raised when a simulated system fails to meet a specified latency or throughput SLA."""
|
|
pass
|