use dist.all_reduce(min) to sync num_blocks_local (#2933)

* pre-commit all files check

* reduce min num_blocks_local

* fix nranks=1

* pre-commit when commit-msg

test/layers/test_sampler.py

@@ -73,6 +73,5 @@ def test_sampler():
     print(next_tokens)
 
 
-
 if __name__ == "__main__":
     test_sampler()