root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-11 13:30:35 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

common : add --no-cont-batching arg (#6358)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-07-15 14:54:58 +03:00
parent fc690b018e
commit 9104bc20ed
No known key found for this signature in database
GPG Key ID: BF970631944C16B7
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
common/common.cpp
View File

@ -797,6 +797,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.cont_batching = true;
return true;
}
if (arg == "-nocb" || arg == "--no-cont-batching") {
params.cont_batching = false;
return true;
}
if (arg == "-fa" || arg == "--flash-attn") {
params.flash_attn = true;
return true;
@ -1538,6 +1542,7 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "*", "-np, --parallel N", "number of parallel sequences to decode (default: %d)", params.n_parallel });
options.push_back({ "*", "-ns, --sequences N", "number of sequences to decode (default: %d)", params.n_sequences });
options.push_back({ "*", "-cb, --cont-batching", "enable continuous batching (a.k.a dynamic batching) (default: %s)", params.cont_batching ? "enabled" : "disabled" });
options.push_back({ "*", "-nocb, --no-cont-batching", "disable continuous batching" });
options.push_back({ "multi-modality" });
options.push_back({ "*", " --mmproj FILE", "path to a multimodal projector file for LLaVA. see examples/llava/README.md" });