Skip to content

fix: harden Megatron optimizer checkpoints - #277

Merged
Yunnglin merged 3 commits into
mainfrom
security/safetensors-checkpoints
Aug 28, 2026
Merged

fix: harden Megatron optimizer checkpoints#277
Yunnglin merged 3 commits into
mainfrom
security/safetensors-checkpoints

Conversation

@Yunnglin

@Yunnglin Yunnglin commented Aug 28, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • remove the online Megatron processor deployment and its CPU-worker startup path
  • persist Megatron LoRA optimizer and RNG state with safetensors plus a JSON manifest, avoiding pickle-based torch.load
  • restore checkpoint loading and serialized DPO reference-log-probability compatibility

Validation

  • /Users/yunlin/miniconda3/envs/twinkle/bin/python -m pytest -q tests/utils/test_safetensors_state_dict.py tests/server/model/test_tinker_compat_output.py

Copilot AI lite review requested due to automatic review settings August 28, 2026 08:22
Copilot AI reviewed Aug 28, 2026

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

@Yunnglin
Yunnglin merged commit 1040a02 into main Aug 28, 2026
3 of 4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

Copilot code review Copilot
Copilot review effort
Applies to this pull request for everyone.Learn more about Copilot code review.
Copilot left review comments
@hjh0119 hjh0119 hjh0119 approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@Yunnglin @hjh0119