Skip to content

batch : fix consistency checks for the input positions #16890

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 31, 2025
Merged

batch : fix consistency checks for the input positions #16890

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 22 additions & 8 deletions src/llama-batch.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,15 +261,29 @@ bool llama_batch_allocr::init(

const llama_pos p0 = memory ? memory->seq_pos_max(s) : -1;

if (p0 >= 0 && p0 >= seq_pos_min(s)) {
LLAMA_LOG_ERROR(
"%s: the tokens of sequence %d in the input batch have inconsistent sequence positions:\n"
" - the last position stored in the memory module of the context (i.e. the KV cache) for sequence %d is X = %d\n"
" - the tokens for sequence %d in the input batch have a starting position of Y = %d\n"
" for M-RoPE, it is required that the position satisfies: X < Y\n",
__func__, s, s, p0, s, seq_pos_min(s));
if (batch.token) {
if (p0 >= 0 && p0 >= seq_pos_min(s)) {
LLAMA_LOG_ERROR(
"%s: the tokens of sequence %d in the input batch have inconsistent sequence positions:\n"
" - the last position stored in the memory module of the context (i.e. the KV cache) for sequence %d is X = %d\n"
" - the tokens for sequence %d in the input batch have a starting position of Y = %d\n"
" for M-RoPE, it is required that the position satisfies: X < Y\n",
__func__, s, s, p0, s, seq_pos_min(s));

return false;
return false;
}
} else {
// embedding inputs can have overlapping positions
if (p0 >= 0 && p0 > seq_pos_min(s)) {
LLAMA_LOG_ERROR(
"%s: the tokens of sequence %d in the input batch have inconsistent sequence positions:\n"
" - the last position stored in the memory module of the context (i.e. the KV cache) for sequence %d is X = %d\n"
" - the tokens for sequence %d in the input batch have a starting position of Y = %d\n"
" for M-RoPE, it is required that the position satisfies: X <= Y\n",
__func__, s, s, p0, s, seq_pos_min(s));

return false;
}
}
}
} else {
Expand Down
Loading