tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 20:29:41 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : allow other bufts when overriding to CPU, add --no-repack option (#14990)

Browse Source
This commit is contained in:
Diego Devesa
2025-07-31 09:11:34 -07:00
committed by GitHub
parent e08a98826b
commit d6818d06a6
5 changed files with 39 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
common/arg.cpp
View File

@@ -2095,6 +2095,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.no_kv_offload = true;
}
).set_env("LLAMA_ARG_NO_KV_OFFLOAD"));
add_opt(common_arg(
{"-nr", "--no-repack"},
"disable weight repacking",
[](common_params & params) {
params.no_extra_bufts = true;
}
).set_env("LLAMA_ARG_NO_REPACK"));
add_opt(common_arg(
{"-ctk", "--cache-type-k"}, "TYPE",
string_format(