Skip to content

llama : validate seq id batch input #13809

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
May 27, 2025
Merged

llama : validate seq id batch input #13809

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4c6ae70
llama : validate seq id batch input
ggerganov May 26, 2025
6995c7e
cont : fix the fix
ggerganov May 26, 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
14 changes: 13 additions & 1 deletion src/llama-context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -693,12 +693,18 @@ int llama_context::encode(llama_batch & inp_batch) {

GGML_ASSERT((!batch.token && batch.embd) || (batch.token && !batch.embd)); // NOLINT

// TODO: move the validation to the llama_batch_allocr
if (batch.token) {
for (int32_t i = 0; i < n_tokens; ++i) {
if (batch.token[i] < 0 || (uint32_t) batch.token[i] >= model.vocab.n_tokens()) {
LLAMA_LOG_ERROR("%s: invalid token[%d] = %d\n", __func__, i, batch.token[i]);
return -1;
}

if (batch.seq_id && (batch.seq_id[i][0] < 0 || batch.seq_id[i][0] >= LLAMA_MAX_PARALLEL_SEQUENCES)) {
LLAMA_LOG_ERROR("%s: invalid seq_id[%d] = %d > %d\n", __func__, i, batch.seq_id[i][0], LLAMA_MAX_PARALLEL_SEQUENCES);
throw -1;
}
}
}

Expand Down Expand Up @@ -887,11 +893,17 @@ int llama_context::decode(llama_batch & inp_batch) {

GGML_ASSERT((!batch.token && batch.embd) || (batch.token && !batch.embd)); // NOLINT

// TODO: move the validation to the llama_batch_allocr
if (batch.token) {
for (int64_t i = 0; i < n_tokens_all; ++i) {
if (batch.token[i] < 0 || (uint32_t) batch.token[i] >= model.vocab.n_tokens()) {
LLAMA_LOG_ERROR("%s: invalid token[%" PRId64 "] = %d\n", __func__, i, batch.token[i]);
throw std::runtime_error("invalid token");
return -1;
}

if (batch.seq_id && (batch.seq_id[i][0] < 0 || batch.seq_id[i][0] >= LLAMA_MAX_PARALLEL_SEQUENCES)) {
LLAMA_LOG_ERROR("%s: invalid seq_id[%" PRId64 "] = %d >= %d\n", __func__, i, batch.seq_id[i][0], LLAMA_MAX_PARALLEL_SEQUENCES);
return -1;
}
}
}
Expand Down
Loading