Enum Error 

pub enum Error {
    ModelNotFound {
        model_id: String,
    },
    UnsupportedArchitecture {
        architecture: String,
    },
    OutOfMemory {
        requested: usize,
        available: usize,
    },
    ContextLengthExceeded {
        current: u32,
        max: u32,
    },
    InvalidConfig {
        message: String,
    },
    Backend {
        backend: String,
        message: String,
    },
    Timeout {
        duration: Duration,
    },
    RateLimited {
        retry_after: Duration,
    },
    Tokenization {
        message: String,
    },
    ModelLoad {
        message: String,
    },
    Io(Error),
    Serialization(Error),
    Internal {
        message: String,
    },
}

Unified error type for the Infernum ecosystem.

Variants

ModelNotFound

Model was not found in the registry.

Fields

model_id: String

The requested model identifier.

UnsupportedArchitecture

Model architecture is not supported.

Fields

architecture: String

The unsupported architecture name.

OutOfMemory

Out of memory during inference.

Fields

requested: usize

Bytes requested.

available: usize

Bytes available.

ContextLengthExceeded

Context length exceeded for the model.

Fields

current: u32

Current token count.

max: u32

Maximum allowed tokens.

InvalidConfig

Invalid configuration provided.

Fields

message: String

Description of the configuration error.

Backend

Backend-specific error.

Fields

backend: String

Backend name (cuda, metal, cpu, etc.).

message: String

Error message.

Timeout

Operation timed out.

Fields

duration: Duration

Duration before timeout.

RateLimited

Rate limited by the system.

Fields

retry_after: Duration

Duration to wait before retrying.

Tokenization

Tokenization error.

Fields

message: String

Error message.

ModelLoad

Model loading error.

Fields

message: String

Error message.

Io(Error)

I/O error.

Serialization(Error)

Serialization error.

Internal

Internal error (unexpected state).

Fields

message: String

Error message.

Implementations

impl Error

pub fn is_retryable(&self) -> bool

Returns true if this error is retryable.

pub fn is_resource_exhaustion(&self) -> bool

Returns true if this error is due to resource exhaustion.

pub fn internal(message: impl Into<String>) -> Self

Creates an internal error with the given message.

pub fn backend(backend: impl Into<String>, message: impl Into<String>) -> Self

Creates a backend error with the given backend name and message.

pub fn model_load(message: impl Into<String>) -> Self

Creates a model load error.

Trait Implementations

impl Debug for Error

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Display for Error

fn fmt(&self, __formatter: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Error for Error

fn source(&self) -> Option<&(dyn Error + 'static)>

Returns the lower-level source of this error, if any.

fn description(&self) -> &str

👎Deprecated since 1.42.0: use the Display impl or to_string()

fn cause(&self) -> Option<&dyn Error>

👎Deprecated since 1.33.0: replaced by Error::source, which can support downcasting

fn provide<'a>(&'a self, request: &mut Request<'a>)

🔬This is a nightly-only experimental API. (error_generic_member_access)

Provides type-based access to context intended for error reports.

impl From<Error> for Error

fn from(source: Error) -> Self

Converts to this type from the input type.

impl From<Error> for Error

fn from(source: Error) -> Self

Converts to this type from the input type.