From 16bc66d9479edd5ee12ec734973554d4493c5dfa Mon Sep 17 00:00:00 2001 From: slaren Date: Thu, 28 Sep 2023 21:42:38 +0200 Subject: llama.cpp : split llama_context_params into model and context params (#3301) * llama.cpp : split llama_context_params into model and context params ggml-ci * fix metal build * fix freq_base/scale default to model value * llama-bench : keep the same model between tests when possible * move n_threads to llama_context_params, add n_threads_batch * fix mpi build * remove kv_size(), cuda scratch fixes * remove low-vram option * add n_threads_batch to system info, refactor to get_system_info() * add documentation about --threads-batch to the READMEs * llama-bench fix * main : fix rope freq/scale warning * llama.cpp : add llama_get_model common : add llama_tokenize from model * remove duplicated ctx/model functions ggml-ci * cuda : print total VRAM used --- examples/beam-search/beam-search.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'examples/beam-search/beam-search.cpp') diff --git a/examples/beam-search/beam-search.cpp b/examples/beam-search/beam-search.cpp index 63da7c3e..f078ab8a 100644 --- a/examples/beam-search/beam-search.cpp +++ b/examples/beam-search/beam-search.cpp @@ -160,7 +160,7 @@ int main(int argc, char ** argv) int n_past = 0; - if (llama_decode(ctx, llama_batch_get_one(tokens_list.data(), tokens_list.size(), n_past, 0), params.n_threads)) + if (llama_decode(ctx, llama_batch_get_one(tokens_list.data(), tokens_list.size(), n_past, 0))) { fprintf(stderr, "%s : failed to eval prompt.\n" , __func__ ); return 1; @@ -170,7 +170,7 @@ int main(int argc, char ** argv) beam_search_callback_data callback_data{ctx, {}}; size_t const beam_width = static_cast(params.n_beams); int const n_predict = 256; - llama_beam_search(ctx, beam_search_callback, &callback_data, beam_width, n_past, n_predict, params.n_threads); + llama_beam_search(ctx, beam_search_callback, &callback_data, beam_width, n_past, n_predict); std::cout << "\n\n"; for (llama_token const token_id : callback_data.response) { -- cgit v1.2.3