tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 14:25:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

correct llama_decode_ext

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-01 14:00:05 +01:00
parent 9e75c49d35
commit 40989f4116
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/common.cpp
View File

@ -1058,7 +1058,7 @@ struct common_init_result common_init_from_params(common_params & params) {
}
if (llama_model_has_decoder(model)) {
llama_batch_ext_ptr batch(llama_batch_ext_init_from_text(tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0, 0));
llama_encode_ext(lctx, batch.get());
llama_decode_ext(lctx, batch.get());
}
llama_kv_cache_clear(lctx);
llama_synchronize(lctx);