mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-08-12 22:29:39 +04:00
Adjust CUDA FA kernel parameters for head size 512 on Turing (#1942)
This commit is contained in:
@@ -1141,8 +1141,8 @@ int main(int argc, char ** argv) {
|
||||
arr.push_back(res->to_json());
|
||||
}
|
||||
// if single request, return single object instead of array
|
||||
res_ok(res, arr.size() == 1 ? arr[0] : arr);
|
||||
}
|
||||
res_ok(res, arr.size() == 1 ? arr[0] : arr);
|
||||
}
|
||||
}
|
||||
else {
|
||||
// in streaming mode, the first error must be treated as non-stream response
|
||||
|
||||
Reference in New Issue
Block a user