server : add help for --flash-attn arg

This commit is contained in:
Georgi Gerganov 2024-04-23 18:16:25 +03:00
parent d228bf8552
commit 751591d520
No known key found for this signature in database
GPG key ID: 449E073F9DC10735

View file

@ -2357,6 +2357,7 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
printf(" --embeddings enable embedding vector output (default: %s)\n", params.embedding ? "enabled" : "disabled"); printf(" --embeddings enable embedding vector output (default: %s)\n", params.embedding ? "enabled" : "disabled");
printf(" -np N, --parallel N number of slots for process requests (default: %d)\n", params.n_parallel); printf(" -np N, --parallel N number of slots for process requests (default: %d)\n", params.n_parallel);
printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: enabled)\n"); printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: enabled)\n");
printf(" -fa, --flash-attn enable Flash Attention (default: %s)\n", params.flash_attn ? "enabled" : "disabled");
printf(" -spf FNAME, --system-prompt-file FNAME\n"); printf(" -spf FNAME, --system-prompt-file FNAME\n");
printf(" set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications.\n"); printf(" set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications.\n");
printf(" -ctk TYPE, --cache-type-k TYPE\n"); printf(" -ctk TYPE, --cache-type-k TYPE\n");