Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-02 11:01:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '9e54e687cbc1500e2097be5b849c03bdc9de6610' into concedo_experimental

Browse Source 
# Conflicts:
#	docs/backend/snapdragon/windows.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-drv.cpp
#	ggml/src/ggml-hexagon/htp-drv.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/fattn-common.hpp
#	ggml/src/ggml-sycl/fattn-onednn.cpp
#	ggml/src/ggml-sycl/fattn-onednn.hpp
#	ggml/src/ggml-sycl/fattn.cpp
#	ggml/src/ggml-sycl/fattn.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-virtgpu/ggml-backend.cpp
#	scripts/snapdragon/build.py
#	tests/test-alloc.cpp
#	tests/test-backend-ops.cpp
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp
This commit is contained in:
Concedo
2026-08-31 18:05:39 +08:00
parent 6f2012b98a 9e54e687cb
commit 4e3a25f3bc
39 changed files with 1175 additions and 227 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+3 -3
View File
@@ -2736,9 +2736,9 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
"- auto: on, but only for tensors larger than 4 GiB\n"
"- off: always keep them resident",
[](common_params & params, const std::string & value) {
/**/ if (value == "on") { params.tensor_read_lazy = LLAMA_TENSOR_READ_LAZY_ON; }
else if (value == "auto") { params.tensor_read_lazy = LLAMA_TENSOR_READ_LAZY_AUTO; }
else if (value == "off") { params.tensor_read_lazy = LLAMA_TENSOR_READ_LAZY_OFF; }
/**/ if (value == "on") { params.lazy_mode = LLAMA_LAZY_MODE_ON; }
else if (value == "auto") { params.lazy_mode = LLAMA_LAZY_MODE_AUTO; }
else if (value == "off") { params.lazy_mode = LLAMA_LAZY_MODE_OFF; }
else { throw std::invalid_argument("invalid value"); }
}
).set_env("LLAMA_ARG_TENSOR_READ_LAZY"));