Skip to content

Commit e966f3b

Browse files
xu-songabetlen
andauthored
feat: Add more detailed log for prefix-match (abetlen#1659)
Co-authored-by: Andrei <abetlen@gmail.com>
1 parent 8432116 commit e966f3b

File tree

1 file changed

+3
-2
lines changed

1 file changed

+3
-2
lines changed

llama_cpp/llama.py

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -777,11 +777,12 @@ def generate(
777777
else:
778778
break
779779
if longest_prefix > 0:
780-
if self.verbose:
781-
print("Llama.generate: prefix-match hit", file=sys.stderr)
782780
reset = False
783781
tokens = tokens[longest_prefix:]
784782
self.n_tokens = longest_prefix
783+
if self.verbose:
784+
print(f"Llama.generate: {longest_prefix} prefix-match hit, "
785+
f"remaining {len(tokens)} prompt tokens to eval", file=sys.stderr)
785786

786787
# Reset the model state
787788
if reset:

0 commit comments

Comments
 (0)
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy