vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit 'acd38efee3' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/cpu.Dockerfile
#	.devops/vulkan.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	CMakeLists.txt
#	README.md
#	cmake/llama-config.cmake.in
#	examples/simple-cmake-pkg/.gitignore
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
This commit is contained in:
Concedo 2025-01-28 18:16:44 +08:00
commit c5d4e07664
11 changed files with 395 additions and 61 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-model.cpp
View file

@ -1314,10 +1314,12 @@ 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)};
};