vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-18 06:19:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	CODEOWNERS
#	common/CMakeLists.txt
#	ggml/CMakeLists.txt
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	scripts/sync-ggml.last
#	tools/cli/cli.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/perplexity/perplexity.cpp
This commit is contained in:
Concedo 2026-04-21 18:53:03 +08:00
commit 19a12bb080
31 changed files with 1594 additions and 1172 deletions
Download patch file Download diff file Expand all files Collapse all files

14
common/arg.cpp
View file

@ -2428,6 +2428,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
}
).set_env("LLAMA_ARG_FIT"));
add_opt(common_arg(
{ "-fitp", "--fit-print" }, "[on|off]",
string_format("print the estimated required memory ('on' or 'off', default: '%s')", params.fit_params_print ? "on" : "off"),
[](common_params & params, const std::string & value) {
if (is_truthy(value)) {
params.fit_params_print = true;
} else if (is_falsey(value)) {
params.fit_params_print = false;
} else {
throw std::runtime_error(
string_format("error: unknown value for --fit-print: '%s'\n", value.c_str()));
}
}
).set_examples({LLAMA_EXAMPLE_FIT_PARAMS}).set_env("LLAMA_ARG_FIT_ESTIMATE"));
add_opt(common_arg(
{ "-fitt", "--fit-target" }, "MiB0,MiB1,MiB2,...",
string_format("target margin per device for --fit, comma-separated list of values, "