diff options
Diffstat (limited to 'common/common.cpp')
| -rw-r--r-- | common/common.cpp | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/common/common.cpp b/common/common.cpp index e938dee1..20cc4a08 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -403,6 +403,18 @@ bool gpt_params_parse_ex(int argc, char ** argv, gpt_params & params) { break; } params.n_sequences = std::stoi(argv[i]); + } else if (arg == "--p-accept" || arg == "-pa") { + if (++i >= argc) { + invalid_param = true; + break; + } + params.p_accept = std::stof(argv[i]); + } else if (arg == "--p-split" || arg == "-ps") { + if (++i >= argc) { + invalid_param = true; + break; + } + params.p_split = std::stof(argv[i]); } else if (arg == "-m" || arg == "--model") { if (++i >= argc) { invalid_param = true; @@ -778,6 +790,8 @@ 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(" -pa N, --p-accept N speculative decoding accept probability (default: %.1f)\n", (double)params.p_accept); + printf(" -ps N, --p-split N speculative decoding split probability (default: %.1f)\n", (double)params.p_split); printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: disabled)\n"); printf(" --mmproj MMPROJ_FILE path to a multimodal projector file for LLaVA. see examples/llava/README.md\n"); printf(" --image IMAGE_FILE path to an image file. use with multimodal models\n"); |