mlx-bun library API
    Preparing search index...

    Module @mlx-bun/inference/artifacts

    FileArtifactIdentityStore
    MmapFile
    SafetensorsFile
    ShardedSafetensors
    ShardedWriter
    WeightAudit
    Weights
    ArtifactIdentityFile
    ArtifactIdentityStore
    Glm52Config
    NamedTensor
    OffloadEntry
    OffloadManifest
    SafetensorsIndex
    ShardInfo
    TensorInfo
    TurboQuantFold
    WeightsNativeBindings
    WeightsOpenOptions
    WeightsView
    WriteOpts
    WriteResult
    Glm52IndexerType
    SafetensorsDtype
    DEFAULT_SHARD_BYTES
    DRAFT_VOCAB_FILE
    DTYPE_SIZE
    TURBOQUANT_FOLD_FILE
    activateExpertOffload
    artifactIdentity
    buildOffloadFile
    configFingerprint
    ensureOffloadFile
    expertOffloadArray
    isExpertOffload
    loadGlm52Config
    modelWeightsIdentity
    parseGlm52Config
    readDraftVocabulary
    readTurboQuantFold
    tensorFingerprint
    tensorUsed
    writeShardedSafetensors
    copyAuxFiles → copyAuxFiles
    KvQuantSpec → KvQuantSpec
    loadModelConfig → loadModelConfig
    ModelConfig → ModelConfig
    parseQuantization → parseQuantization
    parseTurboQuantScheme → parseTurboQuantScheme
    quantFor → quantFor
    QuantizationConfig → QuantizationConfig
    QuantSpec → QuantSpec
    RopeParams → RopeParams
    TextConfig → TextConfig
    TrellisSpec → TrellisSpec
    TURBOQUANT_VALID_KBITS → TURBOQUANT_VALID_KBITS
    TURBOQUANT_VALID_VBITS → TURBOQUANT_VALID_VBITS
    TurboQuantScheme → TurboQuantScheme

    Settings
    Member Visibility

    On This Page
    Classes
    Interfaces
    Type Aliases
    Variables
    Functions
    References