vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-08 01:41:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	common/common.cpp
#	examples/batched-bench/batched-bench.cpp
#	examples/batched/batched.cpp
#	examples/export-lora/export-lora.cpp
#	examples/gritlm/gritlm.cpp
#	examples/parallel/parallel.cpp
#	examples/passkey/passkey.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-cann/acl_tensor.cpp
#	ggml/src/ggml-cann/acl_tensor.h
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	tests/test-arg-parser.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2025-04-03 18:57:49 +08:00
commit 103d60ed2c
43 changed files with 1509 additions and 1129 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -449,7 +449,8 @@ llama_model_loader::llama_model_loader(
std::vector<std::string> & splits,
bool use_mmap,
bool check_tensors,
const struct llama_model_kv_override * param_overrides_p) {
const llama_model_kv_override * param_overrides_p,
const llama_model_tensor_buft_override * param_tensor_buft_overrides_p) {
int trace = 0;
if (getenv("LLAMA_TRACE")) {
trace = atoi(getenv("LLAMA_TRACE"));
@ -461,6 +462,8 @@ llama_model_loader::llama_model_loader(
}
}
tensor_buft_overrides = param_tensor_buft_overrides_p;
// Load the main GGUF
struct ggml_context * ctx = NULL;
struct gguf_init_params params = {
@ -605,7 +608,9 @@ llama_model_loader::llama_model_loader(
if (trace > 0) {
const uint16_t sid = w.idx;
LLAMA_LOG_INFO("%s: - tensor split %2d: %32s %-8s [ %s ]\n", __func__, sid, ggml_get_name(tensor), ggml_type_name(type), llama_format_tensor_shape(tensor).c_str());
LLAMA_LOG_INFO("%s: - tensor split %2d: %32s %-8s [ %s ] %8.2f MiB\n", __func__,
sid, ggml_get_name(tensor), ggml_type_name(type), llama_format_tensor_shape(tensor).c_str(),
ggml_nbytes(tensor)/1024.0f/1024.0f);
}
}
@ -645,9 +650,9 @@ llama_model_loader::llama_model_loader(
ftype = (llama_ftype) (ftype | LLAMA_FTYPE_GUESSED);
{
const int kid = gguf_find_key(meta.get(), "general.file_type"); // TODO: use LLM_KV
if (kid >= 0) {
ftype = (llama_ftype) gguf_get_val_u32(meta.get(), kid);
uint32_t ftype_val = 0;
if (get_key(LLM_KV_GENERAL_FILE_TYPE, ftype_val, false)) {
ftype = (llama_ftype) ftype_val;
}
}