Skip to content

server : fix format_infill #10724

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 8 commits into from
Dec 8, 2024
Merged

server : fix format_infill #10724

Changes from 3 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
b46dc2f
server : fix format_infill
ngxson Dec 8, 2024
6ec3f77
fix
ngxson Dec 8, 2024
a4d2572
rename
ngxson Dec 8, 2024
ac2ea53
update test
ngxson Dec 8, 2024
5ffc2a0
use another model
ngxson Dec 8, 2024
d47360e
update test
ngxson Dec 8, 2024
055aa9e
update test
ngxson Dec 8, 2024
3a81c60
test_invalid_input_extra_req
ngxson Dec 8, 2024
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
22 changes: 22 additions & 0 deletions examples/server/server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3482,6 +3482,11 @@ int main(int argc, char ** argv) {
json data = json::parse(req.body);

// validate input
if (data.contains("prompt") && !data.at("prompt").is_string()) {
// prompt is optional
res_error(res, format_error_response("\"prompt\" must be a string", ERROR_TYPE_INVALID_REQUEST));
}

if (!data.contains("input_prefix")) {
res_error(res, format_error_response("\"input_prefix\" is required", ERROR_TYPE_INVALID_REQUEST));
}
Expand All @@ -3491,9 +3496,11 @@ int main(int argc, char ** argv) {
}

if (data.contains("input_extra") && !data.at("input_extra").is_array()) {
// input_extra is optional
res_error(res, format_error_response("\"input_extra\" must be an array of {\"filename\": string, \"text\": string}", ERROR_TYPE_INVALID_REQUEST));
return;
}

json input_extra = json_value(data, "input_extra", json::array());
for (const auto & chunk : input_extra) {
// { "text": string, "filename": string }
Expand All @@ -3509,6 +3516,21 @@ int main(int argc, char ** argv) {
}
data["input_extra"] = input_extra; // default to empty array if it's not exist

std::string prompt = json_value(data, "prompt", std::string());
std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.ctx, prompt, true, true);
Copy link
Member

Choose a reason for hiding this comment

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

We should probably return an error if there is more than 1 resulting prompt?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Because above we already checked if data["prompt"] is string, here we can be sure that we only have one single prompt to deal with. Probably an GGML_ASSERT here make more sense?

(The expected behavior of tokenize_input_prompts is that if prompt is a string, then output vector size is == 1)

Copy link
Member

Choose a reason for hiding this comment

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

Got it. It's fine as it is.

SRV_DBG("creating infill tasks, n_prompts = %d\n", (int) tokenized_prompts.size());
data["prompt"] = format_infill(
ctx_server.ctx,
data.at("input_prefix"),
data.at("input_suffix"),
data.at("input_extra"),
ctx_server.params_base.n_batch,
ctx_server.params_base.n_predict,
ctx_server.slots[0].n_ctx, // TODO: there should be a better way
ctx_server.params_base.spm_infill,
tokenized_prompts[0]
);

return handle_completions_generic(SERVER_TASK_TYPE_INFILL, data, res);
};

Expand Down
Loading