Function quantizedMatmulQT

quantizedMatmulQT(
    x: MlxArray,
    qt: QuantizedTensor,
    transpose: boolean,
    groupSize: number,
    bits: number,
    s?: bigint,
): MlxArray
quantized_matmul against a quantized tensor (x @ qt^T or x @ qt).
Parameters
- x: MlxArray
- qt: QuantizedTensor
- transpose: boolean
- groupSize: number
- bits: number
- s: bigint = gpuStream
Returns MlxArray
- Defined in packages/mlx/src/ops.ts:890