pub enum Ceiling {
ContextLength,
DeviceMemory,
}Expand description
Which ceiling a rejection hit. The point of naming it is that the
two send an operator to different knobs: ContextLength is the
request’s fault and shrinking the prompt fixes it, DeviceMemory
is the machine’s and only a smaller model / smaller n_ctx /
bigger box does.
Variants§
ContextLength
The request asked for more context than this deployment admitted.
DeviceMemory
weights + KV + headroom does not fit the backend’s budget.
Implementations§
Trait Implementations§
impl Copy for Ceiling
impl Eq for Ceiling
impl StructuralPartialEq for Ceiling
Auto Trait Implementations§
impl Freeze for Ceiling
impl RefUnwindSafe for Ceiling
impl Send for Ceiling
impl Sync for Ceiling
impl Unpin for Ceiling
impl UnsafeUnpin for Ceiling
impl UnwindSafe for Ceiling
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
Mutably borrows from an owned value. Read more
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
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> ⓘ
Converts
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> ⓘ
Converts
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