tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-27 11:43:35 -04:00
Code Issues Packages Projects Releases Wiki Activity

server : pre-calculate EOG logit biases (#14721)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-16 14:04:12 +03:00
committed by GitHub
parent e4841d24d3
commit 6ffd4e9c44
3 changed files with 17 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
common/common.cpp
View File

@ -1005,15 +1005,21 @@ struct common_init_result common_init_from_params(common_params & params) {
params.sampling.ignore_eos = false;
}
if (params.sampling.ignore_eos) {
for (llama_token i = 0; i < llama_vocab_n_tokens(vocab); i++) {
if (llama_vocab_is_eog(vocab, i)) {
LOG_INF("%s: added %s logit bias = %f\n", __func__, common_token_to_piece(lctx, i).c_str(), -INFINITY);
params.sampling.logit_bias.push_back({i, -INFINITY});
}
// initialize once
for (llama_token i = 0; i < llama_vocab_n_tokens(vocab); i++) {
if (llama_vocab_is_eog(vocab, i)) {
LOG_INF("%s: added %s logit bias = %f\n", __func__, common_token_to_piece(lctx, i).c_str(), -INFINITY);
params.sampling.logit_bias_eog.push_back({i, -INFINITY});
}
}
if (params.sampling.ignore_eos) {
// add EOG biases to the active set of logit biases
params.sampling.logit_bias.insert(
params.sampling.logit_bias.end(),
params.sampling.logit_bias_eog.begin(), params.sampling.logit_bias_eog.end());
}
if (params.sampling.penalty_last_n == -1) {
LOG_INF("%s: setting penalty_last_n to ctx_size = %d\n", __func__, llama_n_ctx(lctx));
params.sampling.penalty_last_n = llama_n_ctx(lctx);