Skip to content

simple-chat : fix context-exceeded condition #14494

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 2 commits into from
Jul 2, 2025
+4 −3
Merged

simple-chat : fix context-exceeded condition #14494

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ed9ca47
simple-chat : fix context-exceeded condition
ggerganov Jul 2, 2025
6bd73e3
cont : fix n_ctx_used computation
ggerganov Jul 2, 2025
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
7 changes: 4 additions & 3 deletions examples/simple-chat/simple-chat.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,14 +114,15 @@ int main(int argc, char ** argv) {
// check if we have enough space in the context to evaluate this batch
int n_ctx = llama_n_ctx(ctx);
int n_ctx_used = llama_memory_seq_pos_max(llama_get_memory(ctx), 0);
if (n_ctx_used + batch.n_tokens > n_ctx) {
if (n_ctx_used + batch.n_tokens >= n_ctx) {
Copy link
Member

@slaren slaren Jul 2, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

To be more precise, I think it would be better to add 1 to the value returned by llama_memory_seq_pos_max.

int n_ctx_used = llama_memory_seq_pos_max(llama_get_memory(ctx), 0) + 1;

printf("\033[0m\n");
fprintf(stderr, "context size exceeded\n");
exit(0);
}

if (llama_decode(ctx, batch)) {
GGML_ABORT("failed to decode\n");
int ret = llama_decode(ctx, batch);
if (ret != 0) {
GGML_ABORT("failed to decode, ret = %d\n", ret);
}

// sample the next token
Expand Down
Loading