From c82742ac9cd96fd34aa961978805c1d8a361d589 Mon Sep 17 00:00:00 2001 From: Matt Pulver Date: Fri, 25 Aug 2023 11:18:48 -0400 Subject: llama : add llama_beam_search() (#2267) * Add llama_beam_search(). * Add '// Beam search' heading to llama.{h,cpp} after llama_grammar_accept_token(). * Add space around * pointers and & references. * Add spaces around comparison and assignment operators. * Prefer west const. * Use llama_ prefix for structs in global namespace. * Delete obsolete comment from an earlier revision. * Change eos to eob in llama_beam and llama_beam_view structs. --- common/common.h | 1 + 1 file changed, 1 insertion(+) (limited to 'common/common.h') diff --git a/common/common.h b/common/common.h index 17d271e6..ce61265f 100644 --- a/common/common.h +++ b/common/common.h @@ -28,6 +28,7 @@ struct gpt_params { int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens. + int32_t n_beams = 0; // if non-zero then use beam search of given width. float rope_freq_base = 10000.0f; // RoPE base frequency float rope_freq_scale = 1.0f; // RoPE frequency scaling factor -- cgit v1.2.3