vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

parallel : rename hot-plug to continuous-batching

Browse source
This commit is contained in:
Georgi Gerganov 2023-09-20 09:24:02 +03:00
parent e1067efbfa
commit a1327c71c6
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
3 changed files with 11 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

8
common/common.cpp
View file

@ -372,8 +372,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
params.multiline_input = true;
} else if (arg == "--simple-io") {
params.simple_io = true;
} else if (arg == "--hot-plug") {
params.hot_plug = true;
} else if (arg == "-cb" || arg == "--cont-batching") {
params.cont_batching = true;
} else if (arg == "--color") {
params.use_color = true;
} else if (arg == "--mlock") {
@ -675,7 +675,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" --chunks N max number of chunks to process (default: %d, -1 = all)\n", params.n_chunks);
printf(" -np N, --parallel N number of parallel sequences to decode (default: %d)\n", params.n_parallel);
printf(" -ns N, --sequences N number of sequences to decode (default: %d)\n", params.n_sequences);
printf(" --hot-plug enable hot-plugging of new sequences for decoding (default: disabled)\n");
printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: disabled)\n");
if (llama_mlock_supported()) {
printf(" --mlock force system to keep model in RAM rather than swapping or compressing\n");
}
@ -1270,7 +1270,7 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
fprintf(stream, "rope_freq_scale: %f # default: 1.0\n", params.rope_freq_scale);
fprintf(stream, "seed: %d # default: -1 (random seed)\n", params.seed);
fprintf(stream, "simple_io: %s # default: false\n", params.simple_io ? "true" : "false");
fprintf(stream, "hot_plug: %s # default: false\n", params.hot_plug ? "true" : "false");
fprintf(stream, "cont_batching: %s # default: false\n", params.cont_batching ? "true" : "false");
fprintf(stream, "temp: %f # default: 0.8\n", params.temp);
const std::vector<float> tensor_split_vector(params.tensor_split, params.tensor_split + LLAMA_MAX_DEVICES);

2
common/common.h
View file

@ -110,7 +110,7 @@ struct gpt_params {
bool interactive_first = false; // wait for user input immediately
bool multiline_input = false; // reverse the usage of `\`
bool simple_io = false; // improves compatibility with subprocesses and limited consoles
bool hot_plug = false; // hot-plug new sequences for decoding
bool cont_batching = false; // insert new sequences for decoding on-the-fly
bool input_prefix_bos = false; // prefix BOS to user inputs, preceding input_prefix
bool ignore_eos = false; // ignore generated EOS tokens