nvml

type FailureInjectorConfig struct {
	GPUUUIDsWithGPULost                           []string
	GPUUUIDsWithGPURequiresReset                  []string
	GPUUUIDsWithFabricStateHealthSummaryUnhealthy []string

	// GPUProductNameOverride overrides the detected GPU product name.
	// This is useful for testing fabric state failure injection on systems where
	// the actual GPU (e.g., H100-PCIe) doesn't support fabric state monitoring.
	// Set this to a product name like "H100-SXM" to simulate a fabric-capable GPU.
	// When set, this affects FabricStateSupported(), FabricManagerSupported(),
	// and memory management capabilities detection.
	GPUProductNameOverride string

	// NVMLDeviceGetDevicesError when true simulates Device().GetDevices() failure.
	// This is useful for testing the "Unable to determine the device handle for GPU: Unknown Error"
	// scenario that occurs when NVML library loads but device enumeration fails (e.g., Xid 79).
	// When enabled, gpud continues running but all nvidia components report unhealthy.
	// ref. https://github.com/leptonai/gpud/pull/1180
	NVMLDeviceGetDevicesError bool
}

type Instance interface {
	// NVMLExists returns true if the NVML library is installed.
	NVMLExists() bool

	// Library returns the NVML library.
	Library() nvmllib.Library

	// Devices returns the current devices in the system.
	// The key is the UUID of the GPU device.
	Devices() map[string]device.Device

	// ProductName returns the product name of the GPU.
	// Note that some machines have nvml library but the driver is not installed,
	// returning empty value for the GPU product name.
	ProductName() string

	// Architecture returns the architecture of the GPU.
	// GB200 may return "NVIDIA-Graphics-Device" for the product name
	// but "blackwell" for architecture.
	Architecture() string

	// Brand returns the brand of the GPU.
	Brand() string

	// DriverVersion returns the driver version of the GPU.
	DriverVersion() string

	// DriverMajor returns the major version of the driver.
	DriverMajor() int

	// CUDAVersion returns the CUDA version of the GPU.
	CUDAVersion() string

	// FabricManagerSupported returns true if the fabric manager is supported.
	FabricManagerSupported() bool

	// FabricStateSupported returns true if NVML fabric state telemetry is
	// available for the product (e.g. GB200 via nvmlDeviceGetGpuFabricInfo*).
	FabricStateSupported() bool

	// GetMemoryErrorManagementCapabilities returns the memory error management capabilities of the GPU.
	GetMemoryErrorManagementCapabilities() nvidiaproduct.MemoryErrorManagementCapabilities

	// Shutdown shuts down the NVML library.
	Shutdown() error

	// InitError returns any error that occurred during NVML initialization.
	// If initialization succeeded, this returns nil.
	// Components should check this and report unhealthy if non-nil.
	// This typically occurs when NVML library loads but device enumeration fails,
	// for example: "error getting device handle for index '4': Unknown Error"
	// which corresponds to nvidia-smi showing:
	// "Unable to determine the device handle for GPU0000:XX:00.0: Unknown Error"
	InitError() error
}

type Op struct {
	// contains filtered or unexported fields
}

type OpOption func(*Op)