Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-17 16:25:01 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	common/CMakeLists.txt
#	docs/backend/SYCL.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/binbcast.cpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/gemm.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
#	ggml/src/gguf.cpp
#	scripts/compare-llama-bench.py
#	tests/CMakeLists.txt
#	tests/test-chat.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2025-05-16 15:30:31 +08:00
parent 6cafc0e73e bc098c3cf0
commit e5d26a2356
47 changed files with 2671 additions and 504 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model-loader.cpp
+12 -7
View File
@@ -473,7 +473,7 @@ 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);
@@ -532,7 +532,7 @@ 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
@@ -827,13 +827,18 @@ 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());