Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	ggml/src/CMakeLists.txt
This commit is contained in:
Concedo
2025-10-11 10:01:43 +08:00
parent bc09f34f66 e60f01d941
commit 6d8f8cd65b
18 changed files with 941 additions and 491 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+8
View File
@@ -1958,6 +1958,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.n_ctx_checkpoints = value;
}
).set_env("LLAMA_ARG_CTX_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"--cache-ram", "-cram"}, "N",
string_format("set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)\n"
"[(more info)](https://github.com/ggml-org/llama.cpp/pull/16391)", params.cache_ram_mib),
[](common_params & params, int value) {
params.cache_ram_mib = value;
}
).set_env("LLAMA_ARG_CACHE_RAM").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"