Struct SpeculativeSamplingPlan 

pub struct SpeculativeSamplingPlan { /* private fields */ }

Speculative-decode verification plan (FlashInfer ChainSpeculativeSampling).

Implementations

impl SpeculativeSamplingPlan

pub fn select( _stream: &Stream, desc: &SpeculativeSamplingDescriptor, _pref: PlanPreference, ) -> Result<Self>

Validate the descriptor.

pub fn can_implement(&self, args: &SpeculativeSamplingArgs<'_>) -> Result<()>

Validate args against the descriptor.

pub fn workspace_size(&self) -> usize

Workspace bytes — always 0.

pub fn sku(&self) -> KernelSku

SKU identity.

pub fn precision_guarantee(&self) -> PrecisionGuarantee

Numerical guarantees.

pub fn run( &self, stream: &Stream, _workspace: Workspace<'_>, args: SpeculativeSamplingArgs<'_>, ) -> Result<()>

Run the accept/reject verification.