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/build.yml
#	.github/workflows/docker.yml
#	README.md
#	build-xcframework.sh
#	common/CMakeLists.txt
#	examples/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-metal/ggml-metal.m
#	ggml/src/ggml-metal/ggml-metal.metal
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/backend.hpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	scripts/compare-llama-bench.py
#	src/CMakeLists.txt
#	src/llama-model.cpp
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-opt.cpp
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/README.md
#	tools/mtmd/clip.cpp
#	tools/rpc/rpc-server.cpp
#	tools/server/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo 2025-05-13 00:28:35 +08:00
commit 21e31e255b
90 changed files with 4390 additions and 1388 deletions
Download patch file Download diff file Expand all files Collapse all files

20
common/arg.cpp
View file

@ -41,7 +41,7 @@ using json = nlohmann::ordered_json;
std::initializer_list<enum llama_example> mmproj_examples = {
LLAMA_EXAMPLE_LLAVA,
// TODO: add LLAMA_EXAMPLE_SERVER when it's ready
LLAMA_EXAMPLE_SERVER,
};
static std::string read_file(const std::string & fname) {
@ -2205,32 +2205,33 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_CONT_BATCHING"));
add_opt(common_arg(
{"--mmproj"}, "FILE",
"path to a multimodal projector file. see tools/mtmd/README.md",
"path to a multimodal projector file. see tools/mtmd/README.md\n"
"note: if -hf is used, this argument can be omitted",
[](common_params & params, const std::string & value) {
params.mmproj.path = value;
}
).set_examples(mmproj_examples));
).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ"));
add_opt(common_arg(
{"--mmproj-url"}, "URL",
"URL to a multimodal projector file. see tools/mtmd/README.md",
[](common_params & params, const std::string & value) {
params.mmproj.url = value;
}
).set_examples(mmproj_examples));
).set_examples(mmproj_examples).set_env("LLAMA_ARG_MMPROJ_URL"));
add_opt(common_arg(
{"--no-mmproj"},
"explicitly disable multimodal projector, useful when using -hf",
[](common_params & params) {
params.no_mmproj = true;
}
).set_examples(mmproj_examples));
).set_examples(mmproj_examples).set_env("LLAMA_ARG_NO_MMPROJ"));
add_opt(common_arg(
{"--no-mmproj-offload"},
"do not offload multimodal projector to GPU",
[](common_params & params) {
params.mmproj_use_gpu = false;
}
).set_examples(mmproj_examples));
).set_examples(mmproj_examples).set_env("LLAMA_ARG_NO_MMPROJ_OFFLOAD"));
add_opt(common_arg(
{"--image"}, "FILE",
"path to an image file. use with multimodal models. Specify multiple times for batching",
@ -2437,6 +2438,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
}
));
add_opt(common_arg(
{"--no-op-offload"},
string_format("disable offloading host tensor operations to device (default: %s)", params.no_op_offload ? "true" : "false"),
[](common_params & params) {
params.no_op_offload = true;
}
));
add_opt(common_arg(
{"--lora"}, "FNAME",
"path to LoRA adapter (can be repeated to use multiple adapters)",