LLM-Inference/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-08-12 22:29:39 +04:00
Code Issues Packages Projects Releases Wiki Activity

Re-enable -ictk | --indexer-cache-type-k

Browse Source
This commit is contained in:
Kawrakow
2026-08-08 16:54:29 +03:00
parent a018e4be5a
commit f7f0982c7b
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+4 -3
View File
@@ -1810,17 +1810,18 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
return true;
}
if (arg == "-ctk" || arg == "--cache-type-k") {
CHECK_ARG
params.cache_type_k = argv[++i];
return true;
}
if (arg == "-ctv" || arg == "--cache-type-v") {
CHECK_ARG
params.cache_type_v = argv[++i];
return true;
}
if (arg == "-ictk" || arg == "--indexer-cache-type-k") {
LLAMA_LOG_WARN("================== Quantized indexer cache has been disabled for now => argument '%s' ignored\n", arg.c_str());
++i;
//params.indexer_cache_type_k = argv[++i];
CHECK_ARG
params.indexer_cache_type_k = argv[++i];
return true;
}
if (arg == "-ctk-first" || arg == "--cache-type-k-first") {