Spec Common State Tracker#
-
class SpecCommonStateTracker#
Tracks the greatest per-slot prefix materialized by both target and draft models.
Public Functions
-
void initialize(DecodingInferenceContext const &context)#
- void materializePending(
- int32_t generationRound,
- int32_t activeBatchSize
- void recordAccepted(
- int32_t const *hostAcceptLengths,
- int32_t activeBatchSize
- void compact(
- std::vector<int32_t> const &batchMapping,
- int32_t oldActiveBatch,
- int32_t newActiveBatch
-
void reset() noexcept#
-
void markDraftPrefillOutputsPending() noexcept#
-
void consumeDraftPrefillOutputs() noexcept#
-
bool draftPrefillOutputsPending() const noexcept#
- bool shouldUsePendingPrefillProposal(
- int32_t generationRound
- std::vector<int32_t> const &commonMaterializedStateLengths(
-
void initialize(DecodingInferenceContext const &context)#