Add Support for Gradient Checkpointing #759
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- oerwrite the gradient_checkpointing_enable to provide our ForwardContext during the recomputation of values during backpropagation - 2 bugs remaining: bottleneck adapter for models with the legacy implementation (BERT) & Parallel. Parallel has the problem that we manipulate the batch dimension and this currently leads to an error
akatief
added a commit
to akatief/adapters
that referenced
this pull request
Nov 11, 2024
calpt
force-pushed
the
fix/gradient_checkpointing
branch
from
5edfd4d to
94df2fe
Compare
docs & style & fixes - albert: skip unsupported tests - deberta(V2): fix embedding bug with inplace operations. - deberta: fix LoRAMergedLinear Bug with device mismatch
lenglaender
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Add Support for Gradient Checkpointing
This PR adds support for gradient checkpointing Gradient checkpointing is a technique that trades computation for memory by recomputing intermediate activations during the backward pass instead of storing them. This is particularly useful when training large models. Because we recompute values during the backpropagation, we need to preserve the original ForwardContext in this phase. I solved this by overwriting the
gradient_checkpointing_enablefunction so that the checkpoint function receives the current ForwardContext as the backward pass context manager.