Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-09 14:29:06 +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
common/common.cpp
+1
View File
@@ -1639,6 +1639,7 @@ struct llama_context_params common_context_params_to_llama(const common_params &
cparams.n_seq_max = params.n_parallel;
cparams.n_rs_seq = params.speculative.need_n_rs_seq();
cparams.n_outputs_max = std::max(params.n_outputs_max, 0);
cparams.n_sampling_outputs_per_seq_max = std::max(params.n_sampling_outputs_per_seq_max, 0);
cparams.n_batch = params.n_batch;
cparams.n_ubatch = params.n_ubatch;
cparams.n_threads = params.cpuparams.n_threads;