diff options
Diffstat (limited to 'examples/server')
-rw-r--r-- | examples/server/bench/bench.py | 1 | ||||
-rw-r--r-- | examples/server/server.cpp | 3 |
2 files changed, 4 insertions, 0 deletions
diff --git a/examples/server/bench/bench.py b/examples/server/bench/bench.py index 6ca637bd..86c5de10 100644 --- a/examples/server/bench/bench.py +++ b/examples/server/bench/bench.py @@ -268,6 +268,7 @@ def start_server_background(args): server_args.extend(['--defrag-thold', "0.1"]) server_args.append('--cont-batching') server_args.append('--metrics') + server_args.append('--flash-attn') server_args.extend(['--log-format', "text"]) args = [str(arg) for arg in [server_path, *server_args]] print(f"bench: starting server with: {' '.join(args)}") diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 01453af2..f60530cf 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -2377,6 +2377,7 @@ 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(" -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(" -fa, --flash-attn enable Flash Attention (default: %s)\n", params.flash_attn ? "enabled" : "disabled"); 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(" -ctk TYPE, --cache-type-k TYPE\n"); @@ -2742,6 +2743,8 @@ 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; |