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 commit '52d42686560a9e8f441f9b9780c8890c37d2802d' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/actions/windows-setup-cuda/action.yml
#	.github/workflows/build-riscv.yml
#	.github/workflows/build-sanitize.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	docs/build-s390x.md
#	docs/build.md
#	ggml/CMakeLists.txt
#	ggml/cmake/common.cmake
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/repack.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-cuda/fattn.cu
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/hvx-sin-cos.h
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-vulkan/ggml-vulkan.cpp
#	pyproject.toml
#	requirements/requirements-convert_legacy_llama.txt
#	requirements/requirements-gguf_editor_gui.txt
#	requirements/requirements-server-bench.txt
#	requirements/requirements-tool_bench.txt
#	scripts/make-release-checks.sh
#	tests/test-backend-ops.cpp
#	tests/test-jinja.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-09-13 23:12:41 +08:00
parent ec68802d55 52d4268656
commit 483a456fd0
44 changed files with 2592 additions and 2018 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
-37
View File
@@ -873,17 +873,6 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
arg.c_str(), e.what(), opt.to_string().c_str()));
}
}
// TODO: remove this check after deprecating --mmap|mlock|dio
auto has_arg = [&](std::initializer_list<const char *> names) {
return std::any_of(names.begin(), names.end(), [&](const char * name) {
return seen_args.count(name);
});
};
if (has_arg({"-lm", "--load-mode"}) &&
has_arg({"--mlock", "--mmap", "--no-mmap", "-dio", "--direct-io", "-ndio", "--no-direct-io"})) {
LOG_WRN("DEPRECATED: `--load-mode` and `--mlock`/`--mmap`/`--direct-io` should not be combined; only the last flag on the command line will take effect\n");
}
};
// parse all CLI args now, so that -hf is available below for remote preset resolution
@@ -2695,32 +2684,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_RPC"));
}
add_opt(common_arg(
{"--mlock"},
"DEPRECATED in favor of `--load-mode`: force system to keep model in RAM rather than swapping or compressing",
[](common_params & params) {
LOG_WRN("DEPRECATED: --mlock is deprecated. use --load-mode mlock instead\n");
params.load_mode = LLAMA_LOAD_MODE_MLOCK;
}
).set_env("LLAMA_ARG_MLOCK"));
add_opt(common_arg(
{"--mmap"},
{"--no-mmap"},
"DEPRECATED in favor of `--load-mode`: whether to memory-map model. (if mmap disabled, slower load but may reduce pageouts if not using mlock)",
[](common_params & params, bool value) {
LOG_WRN("DEPRECATED: --mmap and --no-mmap are deprecated. use --load-mode mmap instead\n");
params.load_mode = value ? LLAMA_LOAD_MODE_MMAP : LLAMA_LOAD_MODE_NONE;
}
).set_env("LLAMA_ARG_MMAP"));
add_opt(common_arg(
{"-dio", "--direct-io"},
{"-ndio", "--no-direct-io"},
"DEPRECATED in favor of `--load-mode`: use DirectIO if available",
[](common_params & params, bool value) {
LOG_WRN("DEPRECATED: --direct-io and --no-direct-io are deprecated. use --load-mode dio instead\n");
params.load_mode = value ? LLAMA_LOAD_MODE_DIRECT_IO : LLAMA_LOAD_MODE_NONE;
}
).set_env("LLAMA_ARG_DIO"));
add_opt(common_arg(
{"-lm", "--load-mode"}, "MODE",
"model loading mode (default: auto)\n"