tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 04:45:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

context : do not clear output buffer on reserve (#13152)

Browse Source 
Co-authored-by: pockers21 <liyang2@uniontech.com>
This commit is contained in:
pockers21
2025-04-28 06:45:40 -07:00
committed by GitHub
parent d2b2031e5f
commit fb0471d175
1 changed files with 0 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-context.cpp
View File

@ -1536,8 +1536,6 @@ int32_t llama_context::output_reserve(int32_t n_outputs) {
// set all ids as invalid (negative) // set all ids as invalid (negative)
std::fill(output_ids.begin(), output_ids.end(), -1); std::fill(output_ids.begin(), output_ids.end(), -1);
ggml_backend_buffer_clear(buf_output.get(), 0);
this->n_outputs = 0; this->n_outputs = 0;
this->n_outputs_max = n_outputs_max; this->n_outputs_max = n_outputs_max;