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 branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	README.md
#	build-xcframework.sh
#	common/CMakeLists.txt
#	examples/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-metal/ggml-metal.m
#	ggml/src/ggml-metal/ggml-metal.metal
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/backend.hpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	scripts/compare-llama-bench.py
#	src/CMakeLists.txt
#	src/llama-model.cpp
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-opt.cpp
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/README.md
#	tools/mtmd/clip.cpp
#	tools/rpc/rpc-server.cpp
#	tools/server/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo 2025-05-13 00:28:35 +08:00
commit 21e31e255b
90 changed files with 4390 additions and 1388 deletions
Download patch file Download diff file Expand all files Collapse all files

22
src/llama-model.cpp
View file

@ -122,6 +122,10 @@ static const std::map<llama_rope_scaling_type, const char *> LLAMA_ROPE_SCALING_
{ LLAMA_ROPE_SCALING_TYPE_LONGROPE, "longrope" },
};
std::string llama_rope_scaling_type_name(llama_rope_scaling_type rope_scaling_type) {
return LLAMA_ROPE_SCALING_TYPES.at(rope_scaling_type);
}
static llama_rope_scaling_type llama_rope_scaling_type_from_string(const std::string & name) {
for (const auto & kv : LLAMA_ROPE_SCALING_TYPES) {
if (kv.second == name) {
@ -304,6 +308,10 @@ static buft_list_t make_cpu_buft_list(const std::vector<ggml_backend_dev_t> & de
// add extra buffer types, only if no GPU device is present
// ref: https://github.com/ggml-org/llama.cpp/issues/12481#issuecomment-2743136094
auto * cpu_dev = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU);
if (cpu_dev == nullptr) {
throw std::runtime_error(format("%s: no CPU backend found", __func__));
}
auto * cpu_reg = ggml_backend_dev_backend_reg(cpu_dev);
auto ggml_backend_dev_get_extra_bufts_fn = (ggml_backend_dev_get_extra_bufts_t)
ggml_backend_reg_get_proc_address(cpu_reg, "ggml_backend_dev_get_extra_bufts");
@ -1496,6 +1504,10 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
clblast_offload_fallback_layers = n_gpu_layers;
i_gpu_start = std::max((int64_t) hparams.n_layer, (int64_t) 0);
#endif
if (cpu_dev == nullptr) {
throw std::runtime_error(format("%s: no CPU backend found", __func__));
}
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 {
const bool is_swa = il < (int) hparams.n_layer && hparams.is_swa(il);
@ -1687,6 +1699,9 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
auto * buft_dev = ggml_backend_buft_get_device(buft);
if (ml.use_mmap && buft_dev && buft == ggml_backend_dev_host_buffer_type(buft_dev)) {
auto * cpu_dev = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU);
if (!cpu_dev) {
throw std::runtime_error("no CPU backend found");
}
buft = ggml_backend_dev_buffer_type(cpu_dev);
}
@ -4218,6 +4233,9 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
if (!dev) {
// FIXME: workaround for CPU backend buft having a NULL device
dev = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_CPU);
if (!dev) {
throw std::runtime_error(format("%s: no CPU backend found", __func__));
}
}
ggml_backend_dev_props props;
ggml_backend_dev_get_props(dev, &props);
@ -4347,7 +4365,7 @@ uint64_t llama_model::n_elements() const {
}
void llama_model::print_info() const {
const char * rope_scaling_type = LLAMA_ROPE_SCALING_TYPES.at(hparams.rope_scaling_type_train);
const std::string rope_scaling_type = llama_rope_scaling_type_name(hparams.rope_scaling_type_train);
auto print_f = [](const std::function<uint32_t(uint32_t)> & f, uint32_t n) {
bool is_var = false;
@ -4408,7 +4426,7 @@ void llama_model::print_info() const {
LLAMA_LOG_INFO("%s: causal attn = %d\n", __func__, hparams.causal_attn);
LLAMA_LOG_INFO("%s: pooling type = %d\n", __func__, hparams.pooling_type);
LLAMA_LOG_INFO("%s: rope type = %d\n", __func__, hparams.rope_type);
LLAMA_LOG_INFO("%s: rope scaling = %s\n", __func__, rope_scaling_type);
LLAMA_LOG_INFO("%s: rope scaling = %s\n", __func__, rope_scaling_type.c_str());
LLAMA_LOG_INFO("%s: freq_base_train = %.1f\n", __func__, hparams.rope_freq_base_train);
LLAMA_LOG_INFO("%s: freq_scale_train = %g\n", __func__, hparams.rope_freq_scale_train);
LLAMA_LOG_INFO("%s: n_ctx_orig_yarn = %u\n", __func__, hparams.n_ctx_orig_yarn);