Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-20 09:38:43 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add a numeric context parameter declaring the maximum outputs one sequence

Browse Source
This commit is contained in:
Gaurav Garg
2026-07-05 02:48:13 +05:30
parent 0eddfa0b4c
commit eab4e8444f
14 changed files with 120 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/lookup/lookup.cpp
+1
View File
@@ -30,6 +30,7 @@ int main(int argc, char ** argv){
const int n_draft = params.speculative.draft.n_max;
params.n_outputs_max = common_speculative_n_outputs_max(params.n_batch, params.n_parallel, n_draft);
params.n_sampling_outputs_per_seq_max = common_speculative_n_outputs_per_seq_max(params.n_batch, n_draft);
// init llama.cpp
llama_backend_init();