happyz
/
gemma.cpp
mirror of https://github.com/google/gemma.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Address review feedback: Fix prefill_tbatch_size and variable placement issues

This commit is contained in:
prajwalc22 2025-04-17 10:15:21 +05:30
parent 27c28cc938
commit f55c321397
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
gemma/run.cc
View File

@ -156,8 +156,7 @@ void ReplGemma(const ThreadingArgs& threading, const InferenceArgs& inference,
std::cout << token_text << std::flush; std::cout << token_text << std::flush;
return true; return true;
}; };
// Flag to check if we should exit after processing non-interactive prompt
bool exit_after_generation = !inference.prompt.empty();
while (true) { // Loop until user quits. while (true) { // Loop until user quits.
tokens_generated_this_turn = 0; tokens_generated_this_turn = 0;
@ -224,7 +223,7 @@ void ReplGemma(const ThreadingArgs& threading, const InferenceArgs& inference,
std::cout << "\n\n"; std::cout << "\n\n";
// Break the loop if in non-interactive mode // Break the loop if in non-interactive mode
if (exit_after_generation) { if (!inference.prompt.empty()) {
break; break;
} }