fix: report true rank in logs via dist-aware helpers

- get_rank/get_world_size fall back to RANK/WORLD_SIZE env instead of hardcoded 0/1, matching torchrun's env-before-init contract
- log filter reuses the helpers so initialized groups show real ranks; local-spawn children previously logged rank=0/8
This commit is contained in:
2026-08-27 13:39:38 +08:00
parent 1c04a0b9fa
commit bbb2d95256
2 changed files with 6 additions and 6 deletions
+4 -2
View File
@@ -1,11 +1,13 @@
import logging
import os
from astrai.parallel.setup import get_rank, get_world_size
class _DistributedContextFilter(logging.Filter):
def filter(self, record: logging.LogRecord) -> bool:
record.rank = os.environ.get("RANK", "0")
record.world_size = os.environ.get("WORLD_SIZE", "1")
record.rank = str(get_rank())
record.world_size = str(get_world_size())
return True