Repository navigation
Eval bug: llama-cli, spurious token added to assistant response #13402
Description
Activity
I noticed this char before, I always just assumed it was a spurious prompt print (since most templates end with
>, but I see now that it's repeating the last processed token of the template.Hi
Is the bug fixed? If not, Can I pick it upHi Is the bug fixed? If not, Can I pick it up
AFAIK no, please do.
Reacted by BashCache- added a commit that references this issue
on Sep 29, 2025 - added a commit that references this issue
on Oct 23, 2025 - added a commit that references this issue
on Oct 29, 2025 - added a commit that references this issue
on Feb 5, 2026 - added a commit that references this issue
on Apr 26, 2026 - added a commit that references this issue
on Jul 5, 2026 - added a commit that references this issue
on Jul 16, 2026 - added a commit that references this issue
on Aug 18, 2026 - added a commit that references this issue
on Oct 5, 2026
Name and Version
version: 5327 (27ebfca)
built with cc (Debian 12.2.0-14) 12.2.0 for x86_64-linux-gnu
Operating systems
Linux
GGML backends
CUDA
Hardware
nvidia
Models
all
Problem description & steps to reproduce
After the user prompt is provided, the code enters this branch:
llama.cpp/tools/main/main.cpp
Line 716 in 0cf6725
No new tokens are generated.
However, the following code assumes that there is a new token and it is inserted in the assistant response:
llama.cpp/tools/main/main.cpp
Line 824 in 0cf6725
First Bad Commit
No response
Relevant log output