mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-08 04:00:22 +00:00
server: support flash_attn param
This commit is contained in:
@@ -2722,6 +2722,8 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
|
||||
params.embedding = true;
|
||||
} else if (arg == "-cb" || arg == "--cont-batching") {
|
||||
params.cont_batching = true;
|
||||
} else if (arg == "-fa" || arg == "--flash-attn") {
|
||||
params.flash_attn = true;
|
||||
} else if (arg == "-np" || arg == "--parallel") {
|
||||
if (++i >= argc) {
|
||||
invalid_param = true;
|
||||
|
||||
Reference in New Issue
Block a user