vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-05 19:49:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix n_gpu_layers allocation errors

Browse source
This commit is contained in:
Li, Zonghang 2025-06-14 18:55:53 +04:00
parent e50b3aa473
commit b5ccd62135
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
common/common.cpp
View file

@ -1421,8 +1421,9 @@ static bool assign_layers_to_device(
if (n_m < static_cast<uint32_t>(std::floor(W * vec_z_gpu[m]))) {
// if there is still free GPU memory
has_free_gpu_memory = true;
} else if (w_m > n_m) {
// if the GPU is overloaded
}
if (w_m > n_m) {
// if layers are offloaded to CPU
has_gpu_overload = true;
}
} else if (!in_set(m, M4)) {