ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-14 12:58:10 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-19 13:39:12 +03:00
parent 05501c218d
commit 6b6cf19c65
8 changed files with 256 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
examples/talk-llama/llama-model-loader.cpp
View File

@ -469,7 +469,7 @@ llama_model_loader::llama_model_loader(
meta.reset(gguf_init_from_file(fname.c_str(), params));
if (!meta) {
throw std::runtime_error(format("%s: failed to load model from %s\n", __func__, fname.c_str()));
throw std::runtime_error(format("%s: failed to load model from %s", __func__, fname.c_str()));
}
get_key(llm_kv(LLM_KV_GENERAL_ARCHITECTURE), arch_name, false);
@ -528,7 +528,7 @@ llama_model_loader::llama_model_loader(
};
gguf_context_ptr ctx_gguf { gguf_init_from_file(fname_split, split_params) };
if (!ctx_gguf) {
throw std::runtime_error(format("%s: failed to load GGUF split from %s\n", __func__, fname_split));
throw std::runtime_error(format("%s: failed to load GGUF split from %s", __func__, fname_split));
}
// check idx
@ -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());