pub struct MemoryEstimate {
pub model_weights_bytes: u64,
pub kv_cache_bytes: u64,
pub runtime_overhead_bytes: u64,
pub total_bytes: u64,
pub fits_in_memory: bool,
}Expand description
Memory usage estimate for model inference.
§Example
use pictor_runtime::convenience::estimate_memory_requirements;
let est = estimate_memory_requirements(
1_000_000_000, // 1 GB model
4096, // max sequence length
8, // KV heads
128, // head dim
36, // layers
);
assert!(est.total_bytes > est.model_weights_bytes);
assert!(est.fits_in_memory);Fields§
§model_weights_bytes: u64Memory required for model weights.
kv_cache_bytes: u64Memory required for KV cache.
runtime_overhead_bytes: u64Estimated runtime overhead (buffers, activations, etc.).
total_bytes: u64Total estimated memory requirement.
fits_in_memory: boolWhether the model fits in available memory (heuristic check).
Trait Implementations§
Source§impl Clone for MemoryEstimate
impl Clone for MemoryEstimate
Source§fn clone(&self) -> MemoryEstimate
fn clone(&self) -> MemoryEstimate
Returns a duplicate of the value. Read more
1.0.0 (const: unstable) · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreAuto Trait Implementations§
impl Freeze for MemoryEstimate
impl RefUnwindSafe for MemoryEstimate
impl Send for MemoryEstimate
impl Sync for MemoryEstimate
impl Unpin for MemoryEstimate
impl UnsafeUnpin for MemoryEstimate
impl UnwindSafe for MemoryEstimate
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
impl<ST, DT> CastableFrom<ST, Initialized, Initialized> for DT
impl<ST, DT> CastableFrom<ST, Uninit, Uninit> for DT
Source§impl<T> CloneToUninit for Twhere
T: Clone,
impl<T> CloneToUninit for Twhere
T: Clone,
impl<A, B, T> HttpServerConnExec<A, B> for Twhere
B: Body,
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>
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