LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

llama : move n_vocab from llama_sampler_data to penalty_sampler (#26520)

Browse Source 
This matches how it is done for logit_bias and mirostat samplers, see
https://github.com/ggml-org/llama.cpp/pull/25262#discussion_r3703951151
This commit is contained in:
Oliver Simons
2026-08-04 09:02:49 +03:00
committed by GitHub
parent 22dc605c4e
commit 935cad6497
6 changed files with 16 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-sampling.cpp
+1 -1
View File
@@ -144,7 +144,7 @@ static void test_penalties(
sampler_tester tester(probs, probs_expected);
auto * sampler = llama_sampler_init_penalties(last_tokens.size(), repeat_penalty, alpha_frequency, alpha_presence);
auto * sampler = llama_sampler_init_penalties((int32_t) probs.size(), (int32_t) last_tokens.size(), repeat_penalty, alpha_frequency, alpha_presence);
for (size_t i = 0; i < last_tokens.size(); i++) {
llama_sampler_accept(sampler, last_tokens[i]);