We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent e7c0cae commit e320a37Copy full SHA for e320a37
torchtitan/distributed/utils.py
@@ -220,7 +220,7 @@ def _get_distributed_backend(job_config):
220
backend = f"{device_type}:{backend},cpu:gloo"
221
return backend
222
223
- TRACE_BUFFER_SIZE = "TORCH_NCCL_TRACE_BUFFER_SIZE"
+ TRACE_BUFFER_SIZE = "TORCH_FR_BUFFER_SIZE"
224
TRACE_FILE = "TORCH_NCCL_DEBUG_INFO_TEMP_FILE"
225
DUMP_ON_TIMEOUT = "TORCH_NCCL_DUMP_ON_TIMEOUT"
226
ASYNC_ERROR_HANDLING = "TORCH_NCCL_ASYNC_ERROR_HANDLING"
0 commit comments