vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 17:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build-linux-cross.yml
#	.github/workflows/build.yml
#	cmake/build-info.cmake
#	common/CMakeLists.txt
#	examples/llava/README.md
#	examples/server/README.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
This commit is contained in:
Concedo 2025-05-02 16:54:15 +08:00
commit d8f1f73dd7
25 changed files with 522 additions and 126 deletions
Download patch file Download diff file Expand all files Collapse all files

5
common/arg.cpp
View file

@ -2784,7 +2784,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_THREADS_HTTP"));
add_opt(common_arg(
{"--cache-reuse"}, "N",
string_format("min chunk size to attempt reusing from the cache via KV shifting (default: %d)", params.n_cache_reuse),
string_format(
"min chunk size to attempt reusing from the cache via KV shifting (default: %d)\n"
"[(card)](https://ggml.ai/f0.png)", params.n_cache_reuse
),
[](common_params & params, int value) {
params.n_cache_reuse = value;
}