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:
#	.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
common/arg.cpp
+35 -6
View File
@@ -2090,11 +2090,22 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
add_opt(common_arg(
{"--mmap"},
{"--no-mmap"},
string_format("whether to memory-map model (if disabled, slower load but may reduce pageouts if not using mlock) (default: %s)", params.use_mmap ? "enabled" : "disabled"),
string_format("whether to memory-map model. Explicitly enabling mmap disables direct-io. (if mmap disabled, slower load but may reduce pageouts if not using mlock) (default: %s)", params.use_mmap ? "enabled" : "disabled"),
[](common_params & params, bool value) {
params.use_mmap = value;
if (value) {
params.use_direct_io = false; // disable direct io when mmap is explicitly enabled
}
}
).set_env("LLAMA_ARG_MMAP"));
add_opt(common_arg(
{"-dio", "--direct-io"},
{"-ndio", "--no-direct-io"},
string_format("use DirectIO if available. Takes precedence over --mmap (default: %s)", params.use_direct_io ? "enabled" : "disabled"),
[](common_params & params, bool value) {
params.use_direct_io = value;
}
).set_env("LLAMA_ARG_DIO"));
add_opt(common_arg(
{"--numa"}, "TYPE",
"attempt optimizations that help on some NUMA systems\n"
@@ -2246,7 +2257,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
std::vector<std::string> split_arg{ it, {} };
if (split_arg.size() >= llama_max_devices()) {
throw std::invalid_argument(
string_format("got %d input configs, but system only has %d devices", (int)split_arg.size(), (int)llama_max_devices())
string_format("got %zu input configs, but system only has %zu devices", split_arg.size(), llama_max_devices())
);
}
for (size_t i = 0; i < llama_max_devices(); ++i) {
@@ -2286,10 +2297,28 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_FIT"));
add_opt(common_arg(
{ "-fitt", "--fit-target" }, "MiB",
string_format("target margin per device for --fit option, default: %zu", params.fit_params_target/(1024*1024)),
[](common_params & params, int value) {
params.fit_params_target = value * size_t(1024*1024);
{ "-fitt", "--fit-target" }, "MiB0,MiB1,MiB2,...",
string_format("target margin per device for --fit, comma-separated list of values, "
"single value is broadcast across all devices, default: %zu", params.fit_params_target[0]/(1024*1024)),
[](common_params & params, const std::string & value) {
std::string arg_next = value;
// split string by , and /
const std::regex regex{ R"([,/]+)" };
std::sregex_token_iterator it{ arg_next.begin(), arg_next.end(), regex, -1 };
std::vector<std::string> split_arg{ it, {} };
if (split_arg.size() >= llama_max_devices()) {
throw std::invalid_argument(
string_format("got %zu input configs, but system only has %zu devices", split_arg.size(), llama_max_devices())
);
}
if (split_arg.size() == 1) {
std::fill(params.fit_params_target.begin(), params.fit_params_target.end(), std::stoul(split_arg[0]) * 1024*1024);
return;
}
for (size_t i = 0; i < split_arg.size(); i++) {
params.fit_params_target[i] = std::stoul(split_arg[i]) * 1024*1024;
}
}
).set_env("LLAMA_ARG_FIT_TARGET"));
add_opt(common_arg(