Int4 Qkv Scale Concat

cudaError_t trt_edgellm::kernel::launchGptqInt4QkvScaleConcat(

void const *qScalesGN,

int32_t qWidth,

void const *kScalesGN,

int32_t kWidth,

void const *vScalesGN,

int32_t vWidth,

int32_t numGroups,

void *output,

cudaStream_t stream

)

Concatenate Q/K/V GPTQ scales into [G,Nq+Nk+Nv].