Skip to content

Fixed segfault when prompt was too long #3661

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

Closed
wants to merge 1 commit into from
Closed

Fixed segfault when prompt was too long #3661

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
24 changes: 14 additions & 10 deletions examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -439,28 +439,32 @@ struct llama_server_context
// if input prompt is too big, truncate like normal
if (num_prompt_tokens >= (size_t)n_ctx)
{
const int n_left = (n_ctx - params.n_keep) / 2;
const int n_left = n_ctx - params.n_keep;
const int n_block_size = n_left / 2;
// Keep n_keep tokens at start of prompt (at most n_ctx - 4)
std::vector<llama_token> new_tokens(prompt_tokens.begin(), prompt_tokens.begin() + params.n_keep);
const int erased_blocks = (num_prompt_tokens - params.n_keep - n_left - 1) / n_left;
new_tokens.insert(new_tokens.end(), prompt_tokens.begin() + params.n_keep + erased_blocks * n_left, prompt_tokens.end());
std::copy(prompt_tokens.end() - n_ctx, prompt_tokens.end(), last_n_tokens.begin());
const int erased_blocks = (num_prompt_tokens - params.n_keep - n_block_size) / n_block_size;
new_tokens.insert(new_tokens.end(), prompt_tokens.begin() + params.n_keep + erased_blocks * n_block_size, prompt_tokens.end());

LOG_VERBOSE("input truncated", {
{"n_ctx", n_ctx},
{"n_keep", params.n_keep},
{"n_left", n_left},
{"new_tokens", tokens_to_str(ctx, new_tokens.cbegin(), new_tokens.cend())},
{"num_prompt_tokens", new_tokens.size()}
});

truncated = true;
prompt_tokens = new_tokens;
num_prompt_tokens = prompt_tokens.size();

GGML_ASSERT(num_prompt_tokens < (size_t)n_ctx);
}
else
{
const size_t ps = num_prompt_tokens;
std::fill(last_n_tokens.begin(), last_n_tokens.end() - ps, 0);
std::copy(prompt_tokens.begin(), prompt_tokens.end(), last_n_tokens.end() - ps);
}

// Initialize last_n_tokens
const size_t ps = num_prompt_tokens;
std::fill(last_n_tokens.begin(), last_n_tokens.end() - ps, 0);
std::copy(prompt_tokens.begin(), prompt_tokens.end(), last_n_tokens.end() - ps);

// compare the evaluated prompt with the new prompt
n_past = common_part(embd, prompt_tokens);
Expand Down