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

Disable quantized indexer cache (#2236)

Browse Source
This commit is contained in:
Kawrakow
2026-08-02 18:07:31 +03:00
committed by GitHub
parent 5692312327
commit 96938a1094
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+2 -1
View File
@@ -1809,7 +1809,8 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
return true;
}
if (arg == "-ictk" || arg == "--indexer-cache-type-k") {
params.indexer_cache_type_k = argv[++i];
LLAMA_LOG_WARN("================== Quantized inexer cache has been disabled for now => argument '%s' ignored\n", arg.c_str());
//params.indexer_cache_type_k = argv[++i];
return true;
}
if (arg == "-ctk-first" || arg == "--cache-type-k-first") {