git/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp synced 2026-05-02 04:12:01 +02:00
Code Issues Packages Projects Releases Wiki Activity

spec : fix vocab compat checks in spec example (#22426)

Browse Source 
* port #22358 PR to examples/speculative/speculative.cpp
* use vocab_[tgt,dft] instead of ctx_[tgt,dft] when logging on draft
  model / target model vocabulary mismatch

Co-authored-by: Petros Sideris <petros.sideris@nokia.com>
This commit is contained in:
Peter Sideris 2026-04-30 08:18:25 +03:00 committed by GitHub
parent d77599234e
commit b42c7fa5b8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
examples/speculative/speculative.cpp
View File

@ -110,13 +110,21 @@ int main(int argc, char ** argv) {
return 1;
}
if (
llama_vocab_get_add_bos(vocab_tgt) != llama_vocab_get_add_bos(vocab_dft) ||
llama_vocab_get_add_eos(vocab_tgt) != llama_vocab_get_add_eos(vocab_dft) ||
llama_vocab_bos(vocab_tgt) != llama_vocab_bos(vocab_dft) ||
llama_vocab_eos(vocab_tgt) != llama_vocab_eos(vocab_dft)
) {
LOG_ERR("%s: draft model special tokens must match target model to use speculation\n", __func__);
if (llama_vocab_get_add_bos(vocab_tgt) != llama_vocab_get_add_bos(vocab_dft) ||
(llama_vocab_get_add_bos(vocab_tgt) && llama_vocab_bos(vocab_tgt) != llama_vocab_bos(vocab_dft))) {
LOG_ERR("%s: draft model bos tokens must match target model to use speculation. add: %d - %d, id: %d - %d)\n",
__func__,
llama_vocab_get_add_bos(vocab_tgt), llama_vocab_get_add_bos(vocab_dft),
llama_vocab_bos(vocab_tgt), llama_vocab_bos(vocab_dft));
return 1;
}
if (llama_vocab_get_add_eos(vocab_tgt) != llama_vocab_get_add_eos(vocab_dft) ||
(llama_vocab_get_add_eos(vocab_tgt) && llama_vocab_eos(vocab_tgt) != llama_vocab_eos(vocab_dft))) {
LOG_ERR("%s: draft model eos tokens must match target model to use speculation. add: %d - %d, id: %d - %d)\n",
__func__,
llama_vocab_get_add_eos(vocab_tgt), llama_vocab_get_add_eos(vocab_dft),
llama_vocab_eos(vocab_tgt), llama_vocab_eos(vocab_dft));
return 1;
}
@ -137,11 +145,12 @@ int main(int argc, char ** argv) {
for (int i = SPEC_VOCAB_CHECK_START_TOKEN_ID; i < std::min(n_vocab_tgt, n_vocab_dft); ++i) {
const char * token_text_tgt = llama_vocab_get_text(vocab_tgt, i);
const char * token_text_dft = llama_vocab_get_text(vocab_dft, i);
if (std::strcmp(token_text_tgt, token_text_dft) != 0) {
LOG_ERR("%s: draft model vocab must match target model to use speculation but ", __func__);
LOG_ERR("token %d content differs - target '%s', draft '%s'\n", i,
common_token_to_piece(ctx_tgt, i).c_str(),
common_token_to_piece(ctx_dft, i).c_str());
common_token_to_piece(vocab_tgt, i).c_str(),
common_token_to_piece(vocab_dft, i).c_str());
return 1;
}
}