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

fix: segfault when logits_all=False. Closes #1319

Browse source
This commit is contained in:
Andrei Betlen 2024-04-03 15:30:31 -04:00
parent f96de6d920
commit 8649d7671b
1 changed files with 10 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
llama_cpp/llama.py
View file

@ -535,14 +535,16 @@ class Llama:
# Save tokens
self.input_ids[n_past : n_past + n_tokens] = batch
# Save logits
rows = n_tokens
cols = self._n_vocab
offset = (
0 if self.context_params.logits_all else n_tokens - 1
) # NOTE: Only save the last token logits if logits_all is False
self.scores[n_past + offset : n_past + n_tokens, :].reshape(-1)[
:
] = self._ctx.get_logits()[offset * cols : rows * cols]
if self.context_params.logits_all:
rows = n_tokens
cols = self._n_vocab
logits = self._ctx.get_logits()[: rows * cols]
self.scores[n_past : n_past + n_tokens, :].reshape(-1)[: :] = logits
else:
rows = 1
cols = self._n_vocab
logits = self._ctx.get_logits()[: rows * cols]
self.scores[n_past + n_tokens - 1, :].reshape(-1)[: :] = logits
# Update n_tokens
self.n_tokens += n_tokens