Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Appearance settings

Commit e975dab

Browse filesBrowse files
committed
fix: Additional fixes for speculative decoding
1 parent 11d9562 commit e975dab
Copy full SHA for e975dab

File tree

Expand file treeCollapse file tree

1 file changed

+1
-1
lines changed
Filter options
Expand file treeCollapse file tree

1 file changed

+1
-1
lines changed

‎llama_cpp/llama.py

Copy file name to clipboardExpand all lines: llama_cpp/llama.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -930,7 +930,7 @@ def generate(
930930

931931
sample_idx += 1
932932
if stopping_criteria is not None and stopping_criteria(
933-
self._input_ids, self._scores[-1, :]
933+
self._input_ids[: sample_idx], self._scores[sample_idx - self.n_tokens, :]
934934
):
935935
return
936936
tokens_or_none = yield token

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.