Int4 Moe Scale Repack#

cudaError_t trt_edgellm::kernel::launchInt4MoeScaleRepackSourceBatch(
uint16_t const *const *firstSources,
uint16_t const *const *secondSources,
uint16_t *marlinOutput,
int32_t count,
int32_t G,
int32_t projectionN,
cudaStream_t stream
)#

Repack non-contiguous expert scales directly from CUDA-mapped checkpoint storage. secondSources is null for a single projection.