Mark UVM config as internal until supported (NVIDIA#652)

Signed-off-by: Jason Lowe <jlowe@nvidia.com>

docs/configs.md

@@ -36,7 +36,6 @@ Name | Description | Default Value
 <a name="memory.gpu.reserve"></a>spark.rapids.memory.gpu.reserve|The amount of GPU memory that should remain unallocated by RMM and left for system use such as memory needed for kernels, kernel launches or JIT compilation.|1073741824
 <a name="memory.host.spillStorageSize"></a>spark.rapids.memory.host.spillStorageSize|Amount of off-heap host memory to use for buffering spilled GPU data before spilling to local disk|1073741824
 <a name="memory.pinnedPool.size"></a>spark.rapids.memory.pinnedPool.size|The size of the pinned memory pool in bytes unless otherwise specified. Use 0 to disable the pool.|0
-<a name="memory.uvm.enabled"></a>spark.rapids.memory.uvm.enabled|UVM or universal memory can allow main host memory to act essentially as swap for device(GPU) memory. This allows the GPU to process more data than fits in memory, but can result in slower processing. This is an experimental feature.|false
 <a name="shuffle.transport.enabled"></a>spark.rapids.shuffle.transport.enabled|When set to true, enable the Rapids Shuffle Transport for accelerated shuffle.|false
 <a name="shuffle.transport.maxReceiveInflightBytes"></a>spark.rapids.shuffle.transport.maxReceiveInflightBytes|Maximum aggregate amount of bytes that be fetched at any given time from peers during shuffle|1073741824
 <a name="shuffle.ucx.managementServerHost"></a>spark.rapids.shuffle.ucx.managementServerHost|The host to be used to start the management server|null

sql-plugin/src/main/scala/com/nvidia/spark/rapids/RapidsConf.scala

@@ -291,13 +291,6 @@ object RapidsConf {
     .booleanConf
     .createWithDefault(true)
 
-  val UVM_ENABLED = conf("spark.rapids.memory.uvm.enabled")
-    .doc("UVM or universal memory can allow main host memory to act essentially as swap " +
-      "for device(GPU) memory. This allows the GPU to process more data than fits in memory, but " +
-      "can result in slower processing. This is an experimental feature.")
-    .booleanConf
-    .createWithDefault(false)
-
   val CONCURRENT_GPU_TASKS = conf("spark.rapids.sql.concurrentGpuTasks")
       .doc("Set the number of tasks that can execute concurrently per GPU. " +
           "Tasks may temporarily block when the number of concurrent tasks in the executor " +
@@ -334,6 +327,14 @@ object RapidsConf {
 
   // Internal Features
 
+  val UVM_ENABLED = conf("spark.rapids.memory.uvm.enabled")
+    .doc("UVM or universal memory can allow main host memory to act essentially as swap " +
+      "for device(GPU) memory. This allows the GPU to process more data than fits in memory, but " +
+      "can result in slower processing. This is an experimental feature.")
+    .internal()
+    .booleanConf
+    .createWithDefault(false)
+
   val EXPORT_COLUMNAR_RDD = conf("spark.rapids.sql.exportColumnarRdd")
     .doc("Spark has no simply way to export columnar RDD data.  This turns on special " +
       "processing/tagging that allows the RDD to be picked back apart into a Columnar RDD.")