Skip to content

Fix M-bridge report generation #778

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

Merged
srivatsankrishnan merged 7 commits into from
Jan 17, 2026
Merged

Fix M-bridge report generation #778

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
094a306
fix bug in report generation log name
srivatsankrishnan Jan 17, 2026
c2d3ec3
fix unit test
srivatsankrishnan Jan 17, 2026
94e41bb
Merge branch 'main' into m-bridge
srivatsankrishnan Jan 17, 2026
07d13e1
fix bug in report generation log name
srivatsankrishnan Jan 17, 2026
59de221
fix unit test
srivatsankrishnan Jan 17, 2026
91f7b35
fix copyright year
srivatsankrishnan Jan 17, 2026
28435e5
Merge remote-tracking branch 'refs/remotes/origin/m-bridge' into m-br…
srivatsankrishnan Jan 17, 2026
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
14 changes: 7 additions & 7 deletions src/cloudai/workloads/megatron_bridge/report_generation_strategy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand Down Expand Up @@ -31,12 +31,12 @@ class MegatronBridgeReportGenerationStrategy(ReportGenerationStrategy):
metrics: ClassVar[list[str]] = ["default", "step-time", "tflops-per-gpu"]

def get_log_file(self) -> Path | None:
log = self.test_run.output_path / "megatron_bridge_launcher.log"
log = self.test_run.output_path / "cloudai_megatron_bridge_launcher.log"
return log if log.is_file() else None

@property
def results_file(self) -> Path:
return self.get_log_file() or (self.test_run.output_path / "megatron_bridge_launcher.log")
return self.get_log_file() or (self.test_run.output_path / "cloudai_megatron_bridge_launcher.log")

def can_handle_directory(self) -> bool:
return self.get_log_file() is not None
Expand Down Expand Up @@ -75,8 +75,8 @@ def generate_report(self) -> None:
log_file, step_times_s, gpu_tflops = self._get_extracted_data()
if not log_file:
logging.error(
"No Megatron-Bridge launcher log file found: %s",
self.test_run.output_path / "megatron_bridge_launcher.log",
"No Megatron-Bridge launcher log file found in: %s",
self.test_run.output_path,
)
return

Expand Down Expand Up @@ -130,8 +130,8 @@ def get_metric(self, metric: str) -> float:
log_file, step_times_s, gpu_tflops = self._get_extracted_data()
if not log_file:
logging.error(
"No Megatron-Bridge launcher log file found: %s",
self.test_run.output_path / "megatron_bridge_launcher.log",
"No Megatron-Bridge launcher log file found in: %s",
self.test_run.output_path,
)
return METRIC_ERROR
if not step_times_s:
Expand Down
4 changes: 2 additions & 2 deletions tests/report_generation_strategy/test_megatron_bridge_report_generation_strategy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand Down Expand Up @@ -38,7 +38,7 @@ def mb_tr(tmp_path: Path) -> TestRun:
"",
]
)
(tr.output_path / "megatron_bridge_launcher.log").write_text(log_content)
(tr.output_path / "cloudai_megatron_bridge_launcher.log").write_text(log_content)
return tr


Expand Down