vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/docker.yml
#	Makefile
#	examples/CMakeLists.txt
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/convert.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/sync-ggml.last
This commit is contained in:
Concedo 2025-05-08 23:07:33 +08:00
commit b6220669f4
14 changed files with 410 additions and 117 deletions
Download patch file Download diff file Expand all files Collapse all files

12
common/arg.cpp
View file

@ -1284,7 +1284,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.use_color = true;
}
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_INFILL, LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_LOOKUP}));
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_LOOKUP}));
add_opt(common_arg(
{"-t", "--threads"}, "N",
string_format("number of threads to use during generation (default: %d)", params.cpuparams.n_threads),
@ -1417,7 +1417,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
add_opt(common_arg(
{"-n", "--predict", "--n-predict"}, "N",
string_format(
ex == LLAMA_EXAMPLE_MAIN || ex == LLAMA_EXAMPLE_INFILL
ex == LLAMA_EXAMPLE_MAIN
? "number of tokens to predict (default: %d, -1 = infinity, -2 = until context filled)"
: "number of tokens to predict (default: %d, -1 = infinity)",
params.n_predict),
@ -1656,7 +1656,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.input_prefix = value;
params.enable_chat_template = false;
}
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_INFILL}));
).set_examples({LLAMA_EXAMPLE_MAIN}));
add_opt(common_arg(
{"--in-suffix"}, "STRING",
"string to suffix after user inputs with (default: empty)",
@ -1664,7 +1664,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.input_suffix = value;
params.enable_chat_template = false;
}
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_INFILL}));
).set_examples({LLAMA_EXAMPLE_MAIN}));
add_opt(common_arg(
{"--no-warmup"},
"skip warming up the model with an empty run",
@ -1681,7 +1681,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.spm_infill = true;
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_INFILL}));
).set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--samplers"}, "SAMPLERS",
string_format("samplers that will be used for generation in the order, separated by \';\'\n(default: %s)", sampler_type_names.c_str()),
@ -2893,7 +2893,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.simple_io = true;
}
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_INFILL}));
).set_examples({LLAMA_EXAMPLE_MAIN}));
add_opt(common_arg(
{"--positive-file"}, "FNAME",
string_format("positive prompts file, one prompt per line (default: '%s')", params.cvector_positive_file.c_str()),