vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : fix extra BOS in infill endpoing

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2025-01-06 14:45:56 +02:00
parent 09186fabbe
commit 011baa4036
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/server.cpp
View file

@ -3797,7 +3797,7 @@ 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);
std::vector<llama_tokens> tokenized_prompts = tokenize_input_prompts(ctx_server.ctx, prompt, false, true);
SRV_DBG("creating infill tasks, n_prompts = %d\n", (int) tokenized_prompts.size());
data["prompt"] = format_infill(
ctx_server.ctx,