Fix multiprocessing pickling error for multi-GPU training #40
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Training with multiple GPUs or multiple epochs was failing with
ValueError: ctypes objects containing pointers cannot be pickled
when PyTorch Lightning attempted to spawn worker processes for distributed training.The root cause was module-level ctypes objects in
nnue_dataset.py
that contained C pointers which cannot be serialized for multiprocessing:Solution:
TrainingDataProvider
__getstate__
/__setstate__
methods to handle pickling safely by excluding ctypes objectsTesting:
The original failing command should now work:
Fixes #39.
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.