DequantStrategy

Strategy for dequantizing compressed K/V during attention.

Entries

Link copied to clipboard

Decompress the full requested tile to FP32 before attention.

Link copied to clipboard

Return raw compressed storage — the backend is responsible for fused dequant+attention. Falls back to FULL_TILE when no backend fusion is available.

Properties

Link copied to clipboard

Returns a representation of an immutable list of all enum entries, in the order they're declared.

Functions

Link copied to clipboard

Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)

Link copied to clipboard

Returns an array containing the constants of this enum type, in the order they're declared.