From e0324285a569d0583cf2f4a07a2402221ee25f58 Mon Sep 17 00:00:00 2001 From: stduhpf Date: Tue, 16 Jan 2024 12:04:32 +0100 Subject: speculative : threading options (#4959) * speculative: expose draft threading * fix usage format * accept -td and -tbd args * speculative: revert default behavior when -td is unspecified * fix trailing whitespace --- common/common.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'common/common.h') diff --git a/common/common.h b/common/common.h index 09646824..1f43e628 100644 --- a/common/common.h +++ b/common/common.h @@ -46,7 +46,9 @@ struct gpt_params { uint32_t seed = -1; // RNG seed int32_t n_threads = get_num_physical_cores(); + int32_t n_threads_draft = -1; int32_t n_threads_batch = -1; // number of threads to use for batch processing (-1 = use n_threads) + int32_t n_threads_batch_draft = -1; int32_t n_predict = -1; // new tokens to predict int32_t n_ctx = 512; // context size int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS) -- cgit v1.2.3