vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

rpc: fix register position (#11424)

Browse source 
Signed-off-by: thxCode <thxcode0824@gmail.com>
This commit is contained in:
Frank Mai 2025-01-26 23:20:34 +08:00 • committed by GitHub
parent 2cc9b8c32c
commit 1d8ee06000
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 13 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-model.cpp
View file

@ -1303,10 +1303,12 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
const int act_gpu_layers = devices.empty() ? 0 : std::min(n_gpu_layers, (int)n_layer + 1);
auto get_layer_buft_list = [&](int il) -> llama_model::impl::layer_dev {
if (il < i_gpu_start || (il - i_gpu_start) >= act_gpu_layers) {
LLAMA_LOG_DEBUG("load_tensors: layer %3d assigned to device %s\n", il, ggml_backend_dev_name(cpu_dev));
return {cpu_dev, &pimpl->cpu_buft_list};
}
const int layer_gpu = std::upper_bound(splits.begin(), splits.begin() + n_devices(), float(il - i_gpu_start)/act_gpu_layers) - splits.begin();
auto * dev = devices.at(layer_gpu);
LLAMA_LOG_DEBUG("load_tensors: layer %3d assigned to device %s\n", il, ggml_backend_dev_name(dev));
return {dev, &pimpl->gpu_buft_list.at(dev)};
};