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Outdated suggestions cannot be applied.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.
Description
Refactors the beam search when --n-best is specified so the retrieval of logits from the GPU is batched.
On a standard transformer with 3 decoder layers, this change saw improvements of up tp 10% when --n-best is specified. It also has the benefit of reducing CPU - GPU communication.
This does not contain a table similar to other PRs from #743 since the model motivating this change is different from the proxy model used in #743.
List of changes:
Added dependencies: none
How to test
Ran regression tests and they passed.
CMake command: cmake .. -DCOMPILE_CPU=on -DCOMPILE_CUDA=on -DUSE_SENTENCEPIECE=on -DUSE_STATIC_LIBS=off -DCOMPILE_SERVER=off -DUSE_FBGEMM=on -DCOMPILE_CUDA_SM35=off -DCOMPILE_CUDA_SM50=off -DCOMPILE_CUDA_SM60=off -DCOMPILE_CUDA_SM70=on -DCOMPILE_CUDA_SM75=off -DCOMPILE_TESTS=on
Ubuntu - 18.04.3 LTS
nvcc - 10.1.243
gcc - 7.5.0
Checklist