fp8_twin_bytes

metrale_model_arch::weight_loader::fp8_residency

Function fp8_twin_bytes 

Source 
pub fn fp8_twin_bytes(n: usize, k: usize) -> usize
Expand description

2026-09-25: Bytes of one FP8 transposed twin: n * k E4M3 bytes plus the FP32 block-scale grid over 128x128 blocks, the two allocations of Fp8Weight::transpose_for_gemm.