onednn_w8a16_fp8(x, qweight, scales[, bias]) W8A16 GEMM — fp16/bf16 activations × FP8_E4M3 weights, per-column scale onednn_w4a16(x, weight, scales, zeros[, bias]) W4A16 GEMM — fp16/bf16 activations × ...
pybind11 - You need to add the pybind11 repo as a submodule to your project (or install it into the OS) vxl To avoid messing with your host machine, you can build ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results