pub struct RuntimeStateEstimate {
pub fixed_state_bytes: u64,
pub bytes_per_position_per_batch: u64,
pub context_state_bytes: u64,
pub multimodal_embedding_bytes: u64,
pub media_execution_workspace_bytes: u64,
pub requested_state_bytes: u64,
pub assumptions: StateMemoryAssumptions,
pub completeness: EstimationCompleteness,
}Expand description
Persistent and transient runtime-state estimate for one request.
Fields§
§fixed_state_bytes: u64Context-independent recurrent/convolution state.
bytes_per_position_per_batch: u64Unbounded bytes added per position before multiplying by batch.
context_state_bytes: u64Persistent context-dependent bytes at the requested length.
multimodal_embedding_bytes: u64Prepared-media embedding bytes retained during prefill.
media_execution_workspace_bytes: u64Conservative media-tower execution workspace.
requested_state_bytes: u64Total modeled state for prompt plus output allowance.
assumptions: StateMemoryAssumptionsEstimator assumptions.
completeness: EstimationCompletenessEstimator coverage.
Trait Implementations§
Source§impl Clone for RuntimeStateEstimate
impl Clone for RuntimeStateEstimate
Source§fn clone(&self) -> RuntimeStateEstimate
fn clone(&self) -> RuntimeStateEstimate
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 moreSource§impl Debug for RuntimeStateEstimate
impl Debug for RuntimeStateEstimate
Source§impl<'de> Deserialize<'de> for RuntimeStateEstimate
impl<'de> Deserialize<'de> for RuntimeStateEstimate
Source§fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
__D: Deserializer<'de>,
Deserialize this value from the given Serde deserializer. Read more
impl Eq for RuntimeStateEstimate
Source§impl PartialEq for RuntimeStateEstimate
impl PartialEq for RuntimeStateEstimate
Source§impl Serialize for RuntimeStateEstimate
impl Serialize for RuntimeStateEstimate
impl StructuralPartialEq for RuntimeStateEstimate
Auto Trait Implementations§
impl Freeze for RuntimeStateEstimate
impl RefUnwindSafe for RuntimeStateEstimate
impl Send for RuntimeStateEstimate
impl Sync for RuntimeStateEstimate
impl Unpin for RuntimeStateEstimate
impl UnsafeUnpin for RuntimeStateEstimate
impl UnwindSafe for RuntimeStateEstimate
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