Files
llama.cpp/common
Lumpiasty a9c986086b common : fractional -ncmoe for tensor-granularity expert placement
Extends --n-cpu-moe to accept a fractional layer count. The integer part
offloads whole layers as before; the fractional part offloads a subset of the
boundary layer expert tensors (gate, then up), keeping down_proj resident.
This realizes ATSInfer tensor-granularity static placement, giving sub-layer
control over expert VRAM residency. Placement-only, lossless.

Assisted-by: Claude
2026-07-26 21:58:43 +02:00
..
2026-05-14 13:05:52 +03:00