CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix server crashes (#2076)

Browse Source
This commit is contained in:
Henri Vasserman
2023-07-04 00:05:23 +03:00
committed by GitHub
parent cc45a7feb8
commit 1cf14ccef1
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/server/server.cpp
View File

@@ -906,7 +906,7 @@ int main(int argc, char ** argv) {
while (llama.has_next_token) {
const completion_token_output token_with_probs = llama.doCompletion();
const std::string token_text = llama_token_to_str(llama.ctx, token_with_probs.tok);
const std::string token_text = token_with_probs.tok == -1 ? "" : llama_token_to_str(llama.ctx, token_with_probs.tok);
stop_pos = llama.findStoppingStrings(llama.generated_text,
token_text.size(), STOP_FULL);
@@ -933,7 +933,7 @@ int main(int argc, char ** argv) {
while (llama.has_next_token) {
const completion_token_output token_with_probs = llama.doCompletion();
const std::string token_text = llama_token_to_str(llama.ctx, token_with_probs.tok);
const std::string token_text = token_with_probs.tok == -1 ? "" : llama_token_to_str(llama.ctx, token_with_probs.tok);
if (llama.multibyte_pending > 0) {
continue;
}