Value Members

1.  final def !=(arg0: Any): Boolean

   Definition Classes

   AnyRef → Any

2.  final def ##(): Int

   Definition Classes

   AnyRef → Any

3.  final def ==(arg0: Any): Boolean

   Definition Classes

   AnyRef → Any

4.  final def asInstanceOf[T0]: T0

   Definition Classes

   Any

5.  val chatTemplate: Param[String]

6.  def clone(): AnyRef

   Attributes

   protected[lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... ) @native()

7.  val defaultGpuLayers: Int

   Attributes

   protected

8.  val defaultMainGpu: Int

   Attributes

   protected

9.  val defragmentationThreshold: FloatParam

10.  val embedding: BooleanParam

11.  final def eq(arg0: AnyRef): Boolean

    Definition Classes

    AnyRef

12.  def equals(arg0: Any): Boolean

    Definition Classes

    AnyRef → Any

13.  def finalize(): Unit

    Attributes

    protected[lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

14.  val flashAttention: BooleanParam

15.  def getChatTemplate: String

16.  final def getClass(): Class[_]

    Definition Classes

    AnyRef → Any

    Annotations

    @native()

17.  def getDefragmentationThreshold: Float

18.  def getEmbedding: Boolean

19.  def getFlashAttention: Boolean

20.  def getGrpAttnN: Int
21.  def getGrpAttnW: Int

22.  def getInputPrefixBos: Boolean

23.  def getLookupCacheDynamicFilePath: String

24.  def getLookupCacheStaticFilePath: String

25.  def getLoraAdapters: Map[String, Float]

26.  def getMainGpu: Int

27.  def getMetadata: String

    Get the metadata for the model

28.  def getMetadataMap: Map[String, String]
29.  def getModelDraft: String

30.  def getModelParameters: ModelParameters

    Attributes

    protected

31.  def getNBatch: Int

32.  def getNChunks: Int

33.  def getNCtx: Int

34.  def getNDraft: Int

35.  def getNGpuLayers: Int

36.  def getNGpuLayersDraft: Int

37.  def getNSequences: Int

38.  def getNThreads: Int

39.  def getNThreadsBatch: Int

40.  def getNThreadsBatchDraft: Int

41.  def getNThreadsDraft: Int

42.  def getNUbatch: Int

43.  def getNoKvOffload: Boolean

44.  def getNuma: String

45.  def getPSplit: Float

46.  def getPoolingType: String

47.  def getRopeFreqBase: Float

48.  def getRopeFreqScale: Float

49.  def getRopeScalingType: String

50.  def getSplitMode: String

51.  def getSystemPrompt: String

52.  def getTensorSplit: Array[Double]

53.  def getUseMlock: Boolean

54.  def getUseMmap: Boolean

55.  def getYarnAttnFactor: Float

56.  def getYarnBetaFast: Float

57.  def getYarnBetaSlow: Float

58.  def getYarnExtFactor: Float

59.  def getYarnOrigCtx: Int

60.  val gpuSplitMode: Param[String]

    Set how to split the model across GPUs

    Set how to split the model across GPUs

    • NONE: No GPU split
    • LAYER: Split the model across GPUs by layer
    • ROW: Split the model across GPUs by rows
61.  val grpAttnN: IntParam

62.  val grpAttnW: IntParam

63.  def hashCode(): Int

    Definition Classes

    AnyRef → Any

    Annotations

    @native()

64.  val inputPrefixBos: BooleanParam

65.  final def isInstanceOf[T0]: Boolean

    Definition Classes

    Any

66.  val logger: Logger

    Attributes

    protected

67.  val lookupCacheDynamicFilePath: Param[String]

68.  val lookupCacheStaticFilePath: Param[String]

69.  val loraAdapters: StructFeature[Map[String, Float]]

70.  val mainGpu: IntParam

71.  val metadata: (HasLlamaCppModelProperties.this)#ProtectedParam[String]
72.  val modelDraft: Param[String]

73.  val nBatch: IntParam

74.  val nChunks: IntParam

75.  val nCtx: IntParam

76.  val nDraft: IntParam

77.  val nGpuLayers: IntParam

78.  val nGpuLayersDraft: IntParam

79.  val nSequences: IntParam

80.  val nThreads: IntParam

81.  val nThreadsBatch: IntParam

82.  val nThreadsBatchDraft: IntParam

83.  val nThreadsDraft: IntParam

84.  val nUbatch: IntParam

85.  final def ne(arg0: AnyRef): Boolean

    Definition Classes

    AnyRef

86.  val noKvOffload: BooleanParam

87.  final def notify(): Unit

    Definition Classes

    AnyRef

    Annotations

    @native()

88.  final def notifyAll(): Unit

    Definition Classes

    AnyRef

    Annotations

    @native()

89.  val numaStrategy: Param[String]

    Set optimization strategies that help on some NUMA systems (if available)

    Set optimization strategies that help on some NUMA systems (if available)

    Available Strategies:

    • DISABLED: No NUMA optimizations
    • DISTRIBUTE: Spread execution evenly over all
    • ISOLATE: Only spawn threads on CPUs on the node that execution started on
    • NUMA_CTL: Use the CPU map provided by numactl
    • MIRROR: Mirrors the model across NUMA nodes
90.  val pSplit: FloatParam

91.  val poolingType: Param[String]

    Set the pooling type for embeddings, use model default if unspecified

    Set the pooling type for embeddings, use model default if unspecified

    • 0 NONE: Don't use any pooling
    • 1 MEAN: Mean Pooling
    • 2 CLS: Choose the CLS token
    • 3 LAST: Choose the last token
92.  val ropeFreqBase: FloatParam

93.  val ropeFreqScale: FloatParam

94.  val ropeScalingType: Param[String]

    Set the RoPE frequency scaling method, defaults to linear unless specified by the model.

    Set the RoPE frequency scaling method, defaults to linear unless specified by the model.

    • UNSPECIFIED: Don't use any scaling
    • LINEAR: Linear scaling
    • YARN: YaRN RoPE scaling
95.  def setChatTemplate(chatTemplate: String): HasLlamaCppModelProperties.this

    The chat template to use

96.  def setDefragmentationThreshold(defragThold: Float): HasLlamaCppModelProperties.this

    Set the KV cache defragmentation threshold

97.  def setEmbedding(embedding: Boolean): HasLlamaCppModelProperties.this

    Whether to load model with embedding support

98.  def setFlashAttention(flashAttention: Boolean): HasLlamaCppModelProperties.this

    Whether to enable Flash Attention

99.  def setGpuSplitMode(splitMode: String): HasLlamaCppModelProperties.this

    Set how to split the model across GPUs

    Set how to split the model across GPUs

    • NONE: No GPU split -LAYER: Split the model across GPUs by layer 2. ROW: Split the model across GPUs by rows
100.  def setGpuSupportIfAvailable(spark: SparkSession): HasLlamaCppModelProperties.this

     Attributes

     protected

101.  def setGrpAttnN(grpAttnN: Int): HasLlamaCppModelProperties.this

     Set the group-attention factor

102.  def setGrpAttnW(grpAttnW: Int): HasLlamaCppModelProperties.this

     Set the group-attention width

103.  def setInputPrefixBos(inputPrefixBos: Boolean): HasLlamaCppModelProperties.this

     Whether to add prefix BOS to user inputs, preceding the --in-prefix string

104.  def setLookupCacheDynamicFilePath(lookupCacheDynamicFilePath: String): HasLlamaCppModelProperties.this

     Set path to dynamic lookup cache to use for lookup decoding (updated by generation)

105.  def setLookupCacheStaticFilePath(lookupCacheStaticFilePath: String): HasLlamaCppModelProperties.this

     Set path to static lookup cache to use for lookup decoding (not updated by generation)

106.  def setLoraAdapters(loraAdapters: HashMap[String, Double]): HasLlamaCppModelProperties.this

     Sets paths to lora adapters with user defined scale.

     Sets paths to lora adapters with user defined scale. (PySpark Override)

107.  def setLoraAdapters(loraAdapters: Map[String, Float]): HasLlamaCppModelProperties.this

     Sets paths to lora adapters with user defined scale.

108.  def setMainGpu(mainGpu: Int): HasLlamaCppModelProperties.this

     Set the GPU that is used for scratch and small tensors

109.  def setMetadata(metadata: String): HasLlamaCppModelProperties.this

     Set the metadata for the model

110.  def setModelDraft(modelDraft: String): HasLlamaCppModelProperties.this

     Set the draft model for speculative decoding

111.  def setNBatch(nBatch: Int): HasLlamaCppModelProperties.this

     Set the logical batch size for prompt processing (must be >=32 to use BLAS)

112.  def setNChunks(nChunks: Int): HasLlamaCppModelProperties.this

     Set the maximal number of chunks to process

113.  def setNCtx(nCtx: Int): HasLlamaCppModelProperties.this

     Set the size of the prompt context

114.  def setNDraft(nDraft: Int): HasLlamaCppModelProperties.this

     Set the number of tokens to draft for speculative decoding

115.  def setNGpuLayers(nGpuLayers: Int): HasLlamaCppModelProperties.this

     Set the number of layers to store in VRAM (-1 - use default)

116.  def setNGpuLayersDraft(nGpuLayersDraft: Int): HasLlamaCppModelProperties.this

     Set the number of layers to store in VRAM for the draft model (-1 - use default)

117.  def setNSequences(nSequences: Int): HasLlamaCppModelProperties.this

     Set the number of sequences to decode

118.  def setNThreads(nThreads: Int): HasLlamaCppModelProperties.this

     Set the number of threads to use during generation

119.  def setNThreadsBatch(nThreadsBatch: Int): HasLlamaCppModelProperties.this

     Set the number of threads to use during batch and prompt processing

120.  def setNThreadsBatchDraft(nThreadsBatchDraft: Int): HasLlamaCppModelProperties.this

     Set the number of threads to use during batch and prompt processing

121.  def setNThreadsDraft(nThreadsDraft: Int): HasLlamaCppModelProperties.this

     Set the number of threads to use during draft generation

122.  def setNUbatch(nUbatch: Int): HasLlamaCppModelProperties.this

     Set the physical batch size for prompt processing (must be >=32 to use BLAS)

123.  def setNoKvOffload(noKvOffload: Boolean): HasLlamaCppModelProperties.this

     Whether to disable KV offload

124.  def setNumaStrategy(numa: String): HasLlamaCppModelProperties.this

     Set optimization strategies that help on some NUMA systems (if available)

     Set optimization strategies that help on some NUMA systems (if available)

     Available Strategies:

     • DISABLED: No NUMA optimizations
     • DISTRIBUTE: spread execution evenly over all
     • ISOLATE: only spawn threads on CPUs on the node that execution started on
     • NUMA_CTL: use the CPU map provided by numactl
     • MIRROR: Mirrors the model across NUMA nodes
125.  def setPSplit(pSplit: Float): HasLlamaCppModelProperties.this

     Set the speculative decoding split probability

126.  def setPoolingType(poolingType: String): HasLlamaCppModelProperties.this

     Set the pooling type for embeddings, use model default if unspecified

     Set the pooling type for embeddings, use model default if unspecified

     • 0 NONE: Don't use any pooling and return token embeddings (if the model supports it)
     • 1 MEAN: Mean Pooling
     • 2 CLS: Choose the CLS token
     • 3 LAST: Choose the last token
127.  def setRopeFreqBase(ropeFreqBase: Float): HasLlamaCppModelProperties.this

     Set the RoPE base frequency, used by NTK-aware scaling

128.  def setRopeFreqScale(ropeFreqScale: Float): HasLlamaCppModelProperties.this

     Set the RoPE frequency scaling factor, expands context by a factor of 1/N

129.  def setRopeScalingType(ropeScalingType: String): HasLlamaCppModelProperties.this

     Set the RoPE frequency scaling method, defaults to linear unless specified by the model.

     Set the RoPE frequency scaling method, defaults to linear unless specified by the model.

     • UNSPECIFIED: Don't use any scaling
     • LINEAR: Linear scaling
     • YARN: YaRN RoPE scaling
130.  def setSystemPrompt(systemPrompt: String): HasLlamaCppModelProperties.this

     Set a system prompt to use

131.  def setTensorSplit(tensorSplit: Array[Double]): HasLlamaCppModelProperties.this

     Set how split tensors should be distributed across GPUs

132.  def setUseMlock(useMlock: Boolean): HasLlamaCppModelProperties.this

     Whether to force the system to keep model in RAM rather than swapping or compressing

133.  def setUseMmap(useMmap: Boolean): HasLlamaCppModelProperties.this

     Whether to use memory-map model (faster load but may increase pageouts if not using mlock)

134.  def setYarnAttnFactor(yarnAttnFactor: Float): HasLlamaCppModelProperties.this

     Set the YaRN scale sqrt(t) or attention magnitude

135.  def setYarnBetaFast(yarnBetaFast: Float): HasLlamaCppModelProperties.this

     Set the YaRN low correction dim or beta

136.  def setYarnBetaSlow(yarnBetaSlow: Float): HasLlamaCppModelProperties.this

     Set the YaRN high correction dim or alpha

137.  def setYarnExtFactor(yarnExtFactor: Float): HasLlamaCppModelProperties.this

     Set the YaRN extrapolation mix factor

138.  def setYarnOrigCtx(yarnOrigCtx: Int): HasLlamaCppModelProperties.this

     Set the YaRN original context size of model

139.  final def synchronized[T0](arg0: ⇒ T0): T0

     Definition Classes

     AnyRef

140.  val systemPrompt: Param[String]

141.  val tensorSplit: DoubleArrayParam

142.  def toString(): String

     Definition Classes

     AnyRef → Any

143.  val useMlock: BooleanParam

144.  val useMmap: BooleanParam

145.  final def wait(): Unit

     Definition Classes

     AnyRef

     Annotations

     @throws( ... )

146.  final def wait(arg0: Long, arg1: Int): Unit

     Definition Classes

     AnyRef

     Annotations

     @throws( ... )

147.  final def wait(arg0: Long): Unit

     Definition Classes

     AnyRef

     Annotations

     @throws( ... ) @native()

148.  val yarnAttnFactor: FloatParam

149.  val yarnBetaFast: FloatParam

150.  val yarnBetaSlow: FloatParam

151.  val yarnExtFactor: FloatParam

152.  val yarnOrigCtx: IntParam