vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix prompt cache saving and chat-persistent rollover (fixes #1670)

Browse source
This commit is contained in:
Evan Jones 2023-06-03 00:41:16 -04:00
parent ffb06a345e
commit c812ff2b8a
1 changed files with 7 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

13
examples/main/main.cpp
View file

@ -202,6 +202,13 @@ int main(int argc, char ** argv) {
}
}
// if we will use the cache for the full prompt without reaching the end of the cache, force
// reevaluation of the last token token to recalculate the cached logits
if (embd_inp.size() && n_matching_session_tokens == embd_inp.size() &&
session_tokens.size() > embd_inp.size()) {
session_tokens.resize(embd_inp.size() - 1);
}
// number of tokens to keep when resetting context
if (params.n_keep < 0 || params.n_keep > (int) embd_inp.size() || params.instruct) {
params.n_keep = (int)embd_inp.size();
@ -360,12 +367,6 @@ int main(int argc, char ** argv) {
}
}
if (i > 0) {
// check if we've used up all the prompt but not all cached tokens
if (embd.size() == i && n_session_consumed < (int) session_tokens.size()) {
// force revaluation of the last token to recalculate logits
i--;
n_past--;
}
embd.erase(embd.begin(), embd.begin() + i);
}
}