Module @mlx-bun/inference/contracts/mlx

References

AdaptiveDraftGateSettings → AdaptiveDraftGateSettings
AssistantAttention → AssistantAttention
AssistantDonors → AssistantDonors
AssistantDrafterModel → AssistantDrafterModel
AssistantDraftStep → AssistantDraftStep
AssistantRowsTarget → AssistantRowsTarget
AttentionCache → AttentionCache
AttentionRead → AttentionRead
AudioEncoder → AudioEncoder
BatchableCache → BatchableCache
BidirectionalAttentionCache → BidirectionalAttentionCache
BlockAttentionCache → BlockAttentionCache
Cache → Cache
CheckpointAttachment → CheckpointAttachment
CommittedAttentionCache → CommittedAttentionCache
CompiledDecodeCache → CompiledDecodeCache
ComposedStorage → ComposedStorage
ContextKV → ContextKV
DecodeSlot → DecodeSlot
DecodeStepInputs → DecodeStepInputs
DecodeStepPlan → DecodeStepPlan
DecodeTrace → DecodeTrace
DeepspecContextAttention → DeepspecContextAttention
DeepspecDrafterModel → DeepspecDrafterModel
DeepspecDraftRows → DeepspecDraftRows
DenoisingTraining → DenoisingTraining
Dflash2ContextAttention → Dflash2ContextAttention
Dflash2DraftBlock → Dflash2DraftBlock
Dflash2DrafterModel → Dflash2DrafterModel
DRAFT_CHECKPOINT_SCHEMA → DRAFT_CHECKPOINT_SCHEMA
DrafterContextKV → DrafterContextKV
DrafterContextProjection → DrafterContextProjection
DrafterOperationRange → DrafterOperationRange
DrafterOperations → DrafterOperations
DrafterRowsStep → DrafterRowsStep
DraftHeadOperations → DraftHeadOperations
DraftProjection → DraftProjection
DraftProjectionKernel → DraftProjectionKernel
DraftProjectionKernels → DraftProjectionKernels
DraftProjectionRange → DraftProjectionRange
DraftRowCheckpoint → DraftRowCheckpoint
DsparkContextAttention → DsparkContextAttention
DsparkDrafterModel → DsparkDrafterModel
DsparkDraftOptions → DsparkDraftOptions
EncoderAttentionCache → EncoderAttentionCache
FastFilterConfig → FastFilterConfig
FlashTrainingAttention → FlashTrainingAttention
GatedDeltaCache → GatedDeltaCache
GatedDeltaHeads → GatedDeltaHeads
GatedDeltaParameters → GatedDeltaParameters
Glm52MlaWeightSource → Glm52MlaWeightSource
Glm52WeightSource → Glm52WeightSource
GradCheckpointRun → GradCheckpointRun
GradCheckpointTraining → GradCheckpointTraining
HeadQuant → HeadQuant
HiddenLayerTapsTarget → HiddenLayerTapsTarget
KvAttentionView → KvAttentionView
KvCodec → KvCodec
KvDonorAttention → KvDonorAttention
KvDonorRows → KvDonorRows
KvMaintenance → KvMaintenance
LatentAttentionCache → LatentAttentionCache
LatentAttentionState → LatentAttentionState
LoraLeaves → LoraLeaves
Mask → Mask
MaskMode → MaskMode
MediaEncoders → MediaEncoders
MediaSidecarProbes → MediaSidecarProbes
MlxCacheLayer → MlxCacheLayer
MlxCapturingForward → MlxCapturingForward
MlxCompiledDecodeStep → MlxCompiledDecodeStep
MlxDeclaredGraph → MlxDeclaredGraph
MlxDecodeState → MlxDecodeState
MlxDenoisingAppendRange → MlxDenoisingAppendRange
MlxDenoisingDecodeRange → MlxDenoisingDecodeRange
MlxDenoisingOperations → MlxDenoisingOperations
MlxDenoisingPrefillRange → MlxDenoisingPrefillRange
MlxEmbeddingsForward → MlxEmbeddingsForward
MlxEmbeddingsRange → MlxEmbeddingsRange
MlxForwardStep → MlxForwardStep
MlxForwardWork → MlxForwardWork
MlxHeadForward → MlxHeadForward
MlxHeadRange → MlxHeadRange
MlxKnownOperations → MlxKnownOperations
MlxKnownRange → MlxKnownRange
MlxKnownSpans → MlxKnownSpans
MlxLayerCapture → MlxLayerCapture
MlxMixedForward → MlxMixedForward
MlxMixedGroupRange → MlxMixedGroupRange
MlxMixedRange → MlxMixedRange
MlxModelMemory → MlxModelMemory
MlxPhaseForward → MlxPhaseForward
MlxPhaseGroup → MlxPhaseGroup
MlxPositionedEmbeddingsForward → MlxPositionedEmbeddingsForward
MlxPositionedEmbeddingsRange → MlxPositionedEmbeddingsRange
MlxPositionedForward → MlxPositionedForward
MlxPositionedRange → MlxPositionedRange
MlxPreparationWork → MlxPreparationWork
MlxPromptInput → MlxPromptInput
MlxPromptRange → MlxPromptRange
MlxRowTable → MlxRowTable
MlxSeparateMixed → MlxSeparateMixed
MlxSequenceForward → MlxSequenceForward
MlxSequenceRange → MlxSequenceRange
MlxTokenPhases → MlxTokenPhases
MlxVerifyForward → MlxVerifyForward
MropeForwardState → MropeForwardState
MropeRequestState → MropeRequestState
NativeMtpHead → NativeMtpHead
PaddedPrefillCache → PaddedPrefillCache
PixelInput → PixelInput
PrefillPadding → PrefillPadding
PrefixLayout → PrefixLayout
PrefixSharedTraining → PrefixSharedTraining
RecurrentMtpForward → RecurrentMtpForward
RecurrentMtpModule → RecurrentMtpModule
RecurrentMtpTarget → RecurrentMtpTarget
ResidualBasis → ResidualBasis
RowBatchCache → RowBatchCache
SegmentedPass → SegmentedPass
SegmentedTraining → SegmentedTraining
SharedKv → SharedKv
SpeculativeRowLayout → SpeculativeRowLayout
targetLacks → targetLacks
TargetPort → TargetPort
TargetView → TargetView
TextEmbeddingModel → TextEmbeddingModel
TrainableGraph → TrainableGraph
TrainingAttentionCache → TrainingAttentionCache
Vision → Vision
VisionEncoder → VisionEncoder
WhisperDecoderCache → WhisperDecoderCache
WhisperDims → WhisperDims
WhisperFastCache → WhisperFastCache
WhisperFastPath → WhisperFastPath
WhisperGraph → WhisperGraph