Update NCCL_ASYNC_ERROR_HANDLING env variable (#3267)

* Update env variable

* Update cli variables according to version

* precommit formatting

---------

Co-authored-by: Pau Riba <pau.riba@helsing.ai>
Co-authored-by: Pau Riba <priba@cvc.uab.cat>

composer/cli/launcher.py

@@ -19,6 +19,7 @@
 
 import psutil
 import torch
+from packaging import version
 
 import composer
 from composer.loggers.mosaicml_logger import (
@@ -317,6 +318,13 @@ def _launch_processes(
     log.info('Starting distributed environment on local node for global_rank(%s-%s)', base_rank, base_rank + nproc - 1)
     log.info('Distributed KV store: tcp://%s:%s', master_addr, master_port)
 
+    nccl_env_variable = {
+        (
+            'NCCL_ASYNC_ERROR_HANDLING' if version.parse(torch.__version__) < version.parse('2.2.0') else 'TORCH_NCCL_ASYNC_ERROR_HANDLING'
+        ):
+            '1',
+    }
+
     for local_rank in range(nproc):
         global_rank = base_rank + local_rank
         if command_mode and module_mode:
@@ -339,7 +347,7 @@ def _launch_processes(
             MASTER_ADDR=master_addr,
             MASTER_PORT=str(master_port),
             PYTHONUNBUFFERED='1',
-            NCCL_ASYNC_ERROR_HANDLING='1',
+            **nccl_env_variable,
         ):
             # Populate the distributed variables in all launcher args
             for arg in training_script_args: