Table of Contents

Namespace DotCompute.Backends.CUDA.RingKernels.Resilience

Classes

KernelFaultEventArgs

Event arguments for kernel fault detection.

KernelHealthStatus

Current health status of a kernel.

KernelPermanentFailureEventArgs

Event arguments for permanent kernel failure.

KernelRecoveryEventArgs

Event arguments for kernel recovery.

RingKernelFaultRecoveryOptions

Configuration options for ring kernel fault recovery and watchdog behavior.

RingKernelWatchdog

Monitors ring kernel health and triggers recovery actions when issues are detected.

WatchdogStatistics

Watchdog statistics.

Enums

CircuitBreakerState

Circuit breaker states.

KernelFaultType

Types of kernel faults that can be detected.