Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 09:15:04 +02:00
Code Issues Packages Projects Releases Wiki Activity

Simpify some of the changes

Browse Source
This commit is contained in:
Gaurav Garg
2026-07-10 21:48:33 +05:30
parent 3e753aa27d
commit 9c22762603
13 changed files with 120 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/speculative/speculative.cpp
+3 -3
View File
@@ -58,10 +58,10 @@ int main(int argc, char ** argv) {
// max number of parallel drafting sequences (i.e. tree branches)
const int n_seq_dft = params.n_parallel;
params.n_outputs_max = common_speculative_n_outputs_max(
const auto output_limits = common_speculative_get_output_limits(
params.n_batch, params.n_parallel, params.speculative.draft.n_max);
params.n_sampling_outputs_per_seq_max = common_speculative_n_outputs_per_seq_max(
params.n_batch, params.speculative.draft.n_max);
params.n_outputs_max = output_limits.total;
params.n_sampling_outputs_per_seq_max = output_limits.per_seq;
// probability threshold for splitting a draft branch (only for n_seq_dft > 1)
const float p_draft_split = params.speculative.draft.p_split;