pub enum InferenceError {
Show 13 variants
ModelNotFound(String),
ModelLoadError(String),
TokenizationError(String),
InferenceError(String),
InvalidInput(String),
IoError(Error),
OrtError(String),
HubError(String),
ExtractionFailed(String),
Overloaded {
active: usize,
max: usize,
},
CandleError(String),
GgufError(String),
BinaryQuantError(String),
}Expand description
Errors that can occur during inference operations.
Variants§
ModelNotFound(String)
Model not found or failed to download
ModelLoadError(String)
Failed to load model weights
TokenizationError(String)
Tokenization error
InferenceError(String)
Inference/forward pass error
InvalidInput(String)
Invalid input
IoError(Error)
IO error
OrtError(String)
ONNX Runtime error
HubError(String)
HuggingFace Hub error
ExtractionFailed(String)
External extraction provider error (EXT-1)
Overloaded
Cross-encoder reranker is at capacity — caller should fall back to unranked results.
Root cause of the LoCoMo SIGTERM (DAK-5893): 8 concurrent bench recall requests saturated the 2-session ONNX pool; the 7th/8th request waited >120s for a mutex slot, triggering client-side timeout + 8 retries = ~19-minute stall per question. Fix: return immediately so the API falls back to unranked results rather than queuing.
CandleError(String)
Candle tensor/model error (requires candle feature).
GgufError(String)
GGUF model loading or quantization error (requires candle feature).
BinaryQuantError(String)
Binary quantization error — dimension mismatch or empty input.
Trait Implementations§
Source§impl Debug for InferenceError
impl Debug for InferenceError
Source§impl Display for InferenceError
impl Display for InferenceError
Source§impl Error for InferenceError
impl Error for InferenceError
Source§fn source(&self) -> Option<&(dyn Error + 'static)>
fn source(&self) -> Option<&(dyn Error + 'static)>
1.0.0 · Source§fn description(&self) -> &str
fn description(&self) -> &str
use the Display impl or to_string()
Source§impl From<Error> for InferenceError
impl From<Error> for InferenceError
Auto Trait Implementations§
impl Freeze for InferenceError
impl !RefUnwindSafe for InferenceError
impl Send for InferenceError
impl Sync for InferenceError
impl Unpin for InferenceError
impl UnsafeUnpin for InferenceError
impl !UnwindSafe for InferenceError
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Source§impl<T> Instrument for T
impl<T> Instrument for T
Source§fn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
Source§fn in_current_span(self) -> Instrumented<Self>
fn in_current_span(self) -> Instrumented<Self>
Source§impl<T> IntoEither for T
impl<T> IntoEither for T
Source§fn into_either(self, into_left: bool) -> Either<Self, Self>
fn into_either(self, into_left: bool) -> Either<Self, Self>
self into a Left variant of Either<Self, Self>
if into_left is true.
Converts self into a Right variant of Either<Self, Self>
otherwise. Read moreSource§fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
self into a Left variant of Either<Self, Self>
if into_left(&self) returns true.
Converts self into a Right variant of Either<Self, Self>
otherwise. Read more