ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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)
std::fill(output_ids.begin(), output_ids.end(), -1);
ggml_backend_buffer_clear(buf_output.get(), 0);
this->n_outputs = 0;
this->n_outputs_max = n_outputs_max;