Property SlotContextSize
SlotContextSize
Token window of a single slot: the longest prompt plus completion one request may occupy. Defaults to 8192. Values below 256 are raised to 256; the model's own trained window caps it at attach.
public int SlotContextSize { get; set; }
Property Value
Remarks
This is PER SLOT, not a total to be divided. The pool's context is this multiplied by SlotCount, plus a small reserve the runtime needs for staging, and is reported through the decoder diagnostics rather than configured directly. Reading answers with the inherited value while SlotContextSizeOverride is null; assigning sets the override.