Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 08:44:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/vulkan.Dockerfile
#	.github/workflows/build.yml
#	ci/run.sh
#	examples/model-conversion/Makefile
#	examples/model-conversion/README.md
#	examples/model-conversion/scripts/causal/compare-logits.py
#	examples/model-conversion/scripts/embedding/run-converted-model.sh
#	examples/model-conversion/scripts/utils/common.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/pr2wt.sh
#	scripts/sync_vendor.py
#	tests/test-arg-parser.cpp
This commit is contained in:
Concedo
2026-01-09 01:23:10 +08:00
parent 956ab99934 15bff84bf5
commit 983baac46b
28 changed files with 2516 additions and 757 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+3 -1
View File
@@ -2549,7 +2549,8 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
bool use_mmap_buffer = true;
LLAMA_LOG_INFO("%s: loading model tensors, this can take a while... (mmap = %s)\n", __func__, ml.use_mmap ? "true" : "false");
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");
// 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);
@@ -8139,6 +8140,7 @@ llama_model_params llama_model_default_params() {
/*.kv_overrides =*/ nullptr,
/*.vocab_only =*/ false,
/*.use_mmap =*/ true,
/*.use_direct_io =*/ true,
/*.use_mlock =*/ false,
/*.check_tensors =*/ false,
/*.use_extra_bufts =*/ true,