Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Fix] move ask for live reco #158

Merged
merged 2 commits into from
Nov 13, 2024
Merged

[Fix] move ask for live reco #158

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8a76e08
move ask for live reco
Jackmin801 Nov 12, 2024
b09768e
need matching wait in reinit
Jackmin801 Nov 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions src/zeroband/comms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,6 +77,10 @@ def __init__(

# Logging
self._optimize_ring_ranks()
if self.live_recovery_rank_src is not None:
self.live_recovery.ask_for_live_ckpt(self.live_recovery_rank_src)
self.global_pg.barrier().wait()

self._logger.info(f"global_pg size : {self.global_pg.size()}, local_pg size: {self.local_pg.size()}")

def __del__(self):
Expand Down Expand Up @@ -263,9 +267,6 @@ def _init_global_pg(self) -> None:
self.global_status = "running"
self._last_resolved_time = self.global_store.get("resolved_time").decode("utf-8")

if self.live_recovery_rank_src is not None:
self.live_recovery.ask_for_live_ckpt(self.live_recovery_rank_src)

self._start_heartbeat()

self._logger.info(
Expand Down Expand Up @@ -421,6 +422,7 @@ def maybe_reinit_global_pg(self, admit_joiners: bool = False) -> bool:
try:
self._create_global_pg()
self._optimize_ring_ranks()
self.global_pg.barrier().wait()
except Exception as e:
self._logger.error(f"Error recreating process group: {e}. Retrying...")
return self.maybe_reinit_global_pg(admit_joiners=admit_joiners)
Expand Down