From bdc548680414ff2453efc997506202fa28cc1b28 Mon Sep 17 00:00:00 2001 From: Giri Anantharaman <giriman@learnfair6000.h2.fair> Date: Wed, 3 Feb 2021 04:48:27 -0800 Subject: [PATCH] Adding initialization for `num_pipelines_per_node` (#1599) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Summary: …hod` to avoid unbounded local error. # Before submitting - [ ] Was this discussed/approved via a Github issue? (no need for typos, doc improvements) - [ ] Did you read the [contributor guideline](https://github.com/pytorch/fairseq/blob/master/CONTRIBUTING.md)? - [ ] Did you make sure to update the docs? - [ ] Did you write any new necessary tests? ## What does this PR do? Adding initialization for `num_pipelines_per_node` in `infer_init_method` in `distributed/utils.py` ## PR review Anyone in the community is free to review the PR once the tests have passed. If we didn't discuss your PR in Github issues there's a high chance it will not be merged. ## Did you have fun? Make sure you had fun coding � Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/1599 Reviewed By: myleott Differential Revision: D26208044 Pulled By: girifb fbshipit-source-id: 98d3c0b70b59a5e0abb027850baa3bc44d9c3c78 --- fairseq/distributed/utils.py | 1 + 1 file changed, 1 insertion(+) diff --git a/fairseq/distributed/utils.py b/fairseq/distributed/utils.py index c39dc6d912..e3d8e1e0d3 100644 --- a/fairseq/distributed/utils.py +++ b/fairseq/distributed/utils.py @@ -47,6 +47,7 @@ def infer_init_method(cfg: DistributedTrainingConfig, force_distributed=False): if cfg.distributed_init_method is not None or cfg.tpu: return + num_pipelines_per_node = None if cfg.pipeline_model_parallel: num_pipeline_devices, num_pipelines_per_node = _pipeline_parallel_pre_init(cfg)