happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

common: mark --split-mode tensor as experimental (#21684)

This commit is contained in:
Johannes Gäßler 2026-04-10 12:27:27 +02:00 committed by GitHub
parent f989a6e39e
commit 0893f50f2d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
common/arg.cpp
View File

@ -2353,7 +2353,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
"- none: use one GPU only\n"
"- layer (default): split layers and KV across GPUs (pipelined)\n"
"- row: split weight across GPUs by rows (parallelized)\n"
"- tensor: split weights and KV across GPUs (parallelized)",
"- tensor: split weights and KV across GPUs (parallelized, EXPERIMENTAL)",
[](common_params & params, const std::string & value) {
if (value == "none") {
params.split_mode = LLAMA_SPLIT_MODE_NONE;