AlpinDale fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119) 2 weeks ago
..
marlin_moe_kernel.h fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119) 2 weeks ago
marlin_moe_kernel_ku4b8.cu fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119) 2 weeks ago
marlin_moe_kernel_ku4b8.h fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119) 2 weeks ago
marlin_moe_kernel_ku8b128.cu fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119) 2 weeks ago
marlin_moe_kernel_ku8b128.h fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119) 2 weeks ago