Struct Fp8Scratch 

pub struct Fp8Scratch {
    pub xq: CudaSlice<u8>,
    pub scales: CudaSlice<f32>,
    pub ws: CudaSlice<u8>,
    /* private fields */
}

Resident scratch for the FP8 prefill GEMM (mirrors CutlassScratch): the quantized activation (grown to the largest m*k seen), the 4-float scale block ([0]=amax, [1]=quant mul, [2]=folded B_SCALE — the GEMM desc holds a POINTER to slot 2, so the buffer must be resident/stable), and the cuBLASLt workspace (64MB, the probe’s size). Single GPU worker => no concurrent use; the Mutex guards lazy build/grow only (matches moe_cache / cutlass_scratch).

Fields

xq: CudaSlice<u8>

scales: CudaSlice<f32>

ws: CudaSlice<u8>