CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : remove llama_kv_cache_view API + remove deprecated (#13653)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-20 16:13:16 +03:00
committed by GitHub
parent b69f1647f9
commit a4090d1174
10 changed files with 1 additions and 390 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
common/arg.cpp
View File

@@ -1452,7 +1452,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.swa_full = true;
}
));
).set_env("LLAMA_ARG_SWA_FULL"));
add_opt(common_arg(
{"--no-context-shift"},
string_format("disables context shift on infinite text generation (default: %s)", params.ctx_shift ? "disabled" : "enabled"),
@@ -2065,13 +2065,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.grp_attn_w = value;
}
).set_env("LLAMA_ARG_GRP_ATTN_W").set_examples({LLAMA_EXAMPLE_MAIN}));
add_opt(common_arg(
{"-dkvc", "--dump-kv-cache"},
"verbose print of the KV cache",
[](common_params & params) {
params.dump_kv_cache = true;
}
));
add_opt(common_arg(
{"-nkvo", "--no-kv-offload"},
"disable KV offload",