Temporarily disable cuda graph based RNN-T greedy inference for r2.0.0rc1 #9904
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
r2.0.0rc1. For very rare input shapes, a cooperative kernel might be used by pytorch for LSTM operations. This does not work within a cuda graph conditional node until CUDA 12.6. Unfortunately CUDA 12.6 is not part of the 24.07 pytorch container release, which this release of nemo is intended for. Signed-off-by: Daniel Galvez <dgalvez@nvidia.com>
github-actions bot
pushed a commit
that referenced
this pull request
Jul 26, 2024
r2.0.0rc1. For very rare input shapes, a cooperative kernel might be used by pytorch for LSTM operations. This does not work within a cuda graph conditional node until CUDA 12.6. Unfortunately CUDA 12.6 is not part of the 24.07 pytorch container release, which this release of nemo is intended for. Signed-off-by: Daniel Galvez <dgalvez@nvidia.com>
dimapihtar
pushed a commit
that referenced
this pull request
Aug 27, 2024
r2.0.0rc1. For very rare input shapes, a cooperative kernel might be used by pytorch for LSTM operations. This does not work within a cuda graph conditional node until CUDA 12.6. Unfortunately CUDA 12.6 is not part of the 24.07 pytorch container release, which this release of nemo is intended for. Signed-off-by: Daniel Galvez <dgalvez@nvidia.com>
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Outdated suggestions cannot be applied.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.
Temporarily disable cuda graph based RNN-T greedy inference for r2.0.0rc1.
For very rare input shapes, a cooperative kernel might be used by
pytorch for LSTM operations. This does not work within a cuda graph
conditional node until CUDA 12.6.
Unfortunately CUDA 12.6 is not part of the 24.07 pytorch container
release, which this release of nemo is intended for.