tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : minor sampling refactor (2) (#9386)

Browse Source
This commit is contained in:
slaren
2024-09-09 17:10:46 +02:00
committed by GitHub
parent 38ca6f644b
commit 5fb5e24811
12 changed files with 115 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/batched/batched.cpp
View File

@ -172,8 +172,6 @@ int main(int argc, char ** argv) {
const llama_token new_token_id = llama_sampler_sample(smpl, ctx, i_batch[i]);
llama_sampler_accept(smpl, new_token_id);
// is it an end of generation? -> mark the stream as finished
if (llama_token_is_eog(model, new_token_id) || n_cur == n_predict) {
i_batch[i] = -1;