tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

sampling : when top-k <= 0 -> noop (#13173)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-04-29 20:22:57 +03:00
committed by GitHub
parent 5a63980117
commit d9d398f84f
2 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-sampling.cpp
View File

@ -232,7 +232,7 @@ static void llama_sampler_top_k_impl(llama_token_data_array * cur_p, int32_t k)
// }
if (k <= 0) {
k = cur_p->size;
return;
}
k = std::min(k, (int) cur_p->size);
@ -298,6 +298,7 @@ static void llama_sampler_top_k_impl(llama_token_data_array * cur_p, int32_t k)
}
cur_p->sorted = true;
}
cur_p->size = k;
}