Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '128d522c04286e019666bd6ee4d18e3fbf8772e2' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	ggml/src/ggml-vulkan/ggml-vulkan.cpp
#	tests/test-alloc.cpp
#	tests/test-chat.cpp
This commit is contained in:
Concedo
2025-10-04 23:51:22 +08:00
parent b8680cd0c5 128d522c04
commit 1d728bbc89
18 changed files with 381 additions and 226 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+5 -5
View File
@@ -1955,13 +1955,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_SWA_FULL"));
add_opt(common_arg(
{"--swa-checkpoints"}, "N",
string_format("max number of SWA checkpoints per slot to create (default: %d)\n"
"[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)", params.n_swa_checkpoints),
{"--ctx-checkpoints", "--swa-checkpoints"}, "N",
string_format("max number of context checkpoints to create per slot (default: %d)\n"
"[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)", params.n_ctx_checkpoints),
[](common_params & params, int value) {
params.n_swa_checkpoints = value;
params.n_ctx_checkpoints = value;
}
).set_env("LLAMA_ARG_SWA_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER}));
).set_env("LLAMA_ARG_CTX_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--kv-unified", "-kvu"},
string_format("use single unified KV buffer for the KV cache of all sequences (default: %s)\n"