Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	AGENTS.md
#	CODEOWNERS
#	CONTRIBUTING.md
#	docs/backend/OPENCL.md
#	docs/development/HOWTO-add-model.md
#	examples/training/finetune.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-drv.cpp
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/dma-queue.c
#	ggml/src/ggml-hexagon/htp/dma-queue.h
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.h
#	ggml/src/ggml-hexagon/htp/hmx-mm-kernels-tiled.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/htp-tensor.c
#	ggml/src/ggml-hexagon/htp/htp-tensor.h
#	ggml/src/ggml-hexagon/htp/hvx-fa-kernels.h
#	ggml/src/ggml-hexagon/htp/hvx-reduce.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.h
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/compare-llama-bench.py
#	scripts/snapdragon/ggml-hexagon-profile.py
#	scripts/snapdragon/ggml-hexagon-trace.py
#	scripts/sync_vendor.py
#	tests/test-arg-parser.cpp
#	tests/test-chat.cpp
#	tests/test-model-load-cancel.cpp
#	tests/test-quantize-stats.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
#	tools/ui/src/lib/constants/settings-registry.ts
This commit is contained in:
Concedo
2026-07-25 12:20:51 +08:00
parent eea06b0a89 ed7adbfefd
commit 49dbdaaab5
81 changed files with 40233 additions and 848 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+5 -6
View File
@@ -16,6 +16,7 @@
#include "llama-memory-hybrid-iswa.h"
#include "llama-memory-recurrent.h"
#include "llama.h"
#include "models/models.h"
#include "ggml.h"
@@ -1383,7 +1384,7 @@ void llama_model_base::load_vocab(llama_model_loader & ml) {
bool llama_model_base::load_tensors(llama_model_loader & ml) {
const auto & split_mode = params.split_mode;
const auto & use_mlock = params.use_mlock;
const bool use_mlock = params.load_mode == LLAMA_LOAD_MODE_MLOCK;
const auto & tensor_split = params.tensor_split;
const int n_layer_all = hparams.n_layer_all;
@@ -1393,8 +1394,8 @@ bool llama_model_base::load_tensors(llama_model_loader & ml) {
this->ml = &ml; // to be used by create_tensor() and load_arch_tensors()
LLAMA_LOG_INFO("%s: loading model tensors, this can take a while... (mmap = %s, direct_io = %s)\n",
__func__, ml.use_mmap ? "true" : "false", ml.use_direct_io ? "true" : "false");
LLAMA_LOG_INFO("%s: loading model tensors, this can take a while... (load_mode = %s)\n",
__func__, llama_load_mode_name(params.load_mode));
// build a list of buffer types for the CPU and GPU devices
pimpl->cpu_buft_list = make_cpu_buft_list(devices, params.use_extra_bufts, params.no_host);
@@ -2458,15 +2459,13 @@ llama_model_params llama_model_default_params() {
/*.tensor_buft_overrides =*/ nullptr,
/*.n_gpu_layers =*/ -1,
/*.split_mode =*/ LLAMA_SPLIT_MODE_LAYER,
/*.load_mode =*/ LLAMA_LOAD_MODE_MMAP,
/*.main_gpu =*/ 0,
/*.tensor_split =*/ nullptr,
/*.progress_callback =*/ nullptr,
/*.progress_callback_user_data =*/ nullptr,
/*.kv_overrides =*/ nullptr,
/*.vocab_only =*/ false,
/*.use_mmap =*/ true,
/*.use_direct_io =*/ false,
/*.use_mlock =*/ false,
/*.check_tensors =*/ false,
/*.use_extra_bufts =*/ true,
/*.no_host =*/ false,