root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 03:14:35 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

server : enable continuous batching by default (#6231)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-03-22 13:08:28 +02:00 committed by GitHub
parent b3e94f26ba
commit 68e210b354
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
common/common.h
View File

@ -139,7 +139,7 @@ struct gpt_params {
bool interactive_first = false; // wait for user input immediately bool interactive_first = false; // wait for user input immediately
bool multiline_input = false; // reverse the usage of `\` bool multiline_input = false; // reverse the usage of `\`
bool simple_io = false; // improves compatibility with subprocesses and limited consoles bool simple_io = false; // improves compatibility with subprocesses and limited consoles
bool cont_batching = false; // insert new sequences for decoding on-the-fly bool cont_batching = true; // insert new sequences for decoding on-the-fly
bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix
bool ignore_eos = false; // ignore generated EOS tokens bool ignore_eos = false; // ignore generated EOS tokens

2
examples/server/server.cpp
View File

@ -2225,7 +2225,7 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
printf(" -to N, --timeout N server read/write timeout in seconds (default: %d)\n", sparams.read_timeout); printf(" -to N, --timeout N server read/write timeout in seconds (default: %d)\n", sparams.read_timeout);
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: disabled)\n"); printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: enabled)\n");
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");