tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

embedding : enable --no-warmup option (#11475)

Browse Source 
This commit enables the `--no-warmup` option for the llama-embeddings.

The motivation for this change is to allow the user to disable the
warmup when running the the program.
This commit is contained in:
Daniel Bevenius
2025-01-29 09:38:54 +01:00
committed by GitHub
parent 325afb370a
commit b636228c0a
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/arg.cpp
View File

@ -877,7 +877,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.warmup = false;
}
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER}));
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_EMBEDDING}));
add_opt(common_arg(
{"--spm-infill"},
string_format(