CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix quantize with dl backends (#13539)

Browse Source
This commit is contained in:
Diego Devesa
2025-05-14 07:12:36 -07:00
committed by GitHub
parent 6da34fa276
commit b7d2672082
1 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/llama-model-loader.cpp
View File

@@ -822,13 +822,18 @@ void llama_model_loader::init_mappings(bool prefetch, llama_mlocks * mlock_mmaps
mappings.reserve(files.size());
mmaps_used.reserve(files.size());
for (const auto & file : files) {
auto * reg = ggml_backend_dev_backend_reg(ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU));
if (!reg) {
throw std::runtime_error(format("%s: no CPU backend found", __func__));
bool is_numa = false;
auto * dev = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU);
if (dev) {
auto * reg = ggml_backend_dev_backend_reg(dev);
auto * is_numa_fn = (decltype(ggml_is_numa) *) ggml_backend_reg_get_proc_address(reg, "ggml_backend_cpu_is_numa");
if (is_numa_fn) {
is_numa = is_numa_fn();
}
}
auto * is_numa_fn = (decltype(ggml_is_numa) *) ggml_backend_reg_get_proc_address(reg, "ggml_backend_cpu_is_numa");
std::unique_ptr<llama_mmap> mapping = std::make_unique<llama_mmap>(file.get(), prefetch ? -1 : 0, is_numa_fn());
std::unique_ptr<llama_mmap> mapping = std::make_unique<llama_mmap>(file.get(), prefetch ? -1 : 0, is_numa);
mmaps_used.emplace_back(mapping->size(), 0);
if (mlock_mmaps) {
std::unique_ptr<llama_mlock> mlock_mmap(new llama_mlock());