fwd optimizations #125
Open
fwd optimizations #125
Conversation
This file contains hidden or 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
Summary: Pull Request resolved: pytorch#4648 X-link: facebookresearch/FBGEMM#1682 Add TBE/VBE bench (-- device-with-speclist) that takes dim lists for args under tbe_training. #### Summary This diff introduces a new feature to the TBE (Table Batched Embedding) bench, which allows for benchmarking with a list of devices and speclist. The changes include: * **tbe_data_config_loader.py:** Added a new class `TBEDataListConfig` to load a list of `TBEDataConfig` objects. Modified the `TBEDataConfigLoader` class to load a list of `TBEDataConfig` objects. * **bench_runs.py:** Added a new function `bench_warmup_with_spec` to perform warm-up runs with a specified list of devices and batch sizes. * **tbe_data_config_param_models.py:** Added a new class `BatchListParams` to represent a list of batch sizes and their corresponding standard deviations. * **__init__.py:** Imported the new `TBEDataListConfig` class and the `benchmark_requests_with_spec` function. * **tbe_training_benchmark.py:** Added a new function `benchmark_requests_with_spec` to benchmark requests with a specified list of devices and batch sizes. These changes enable the TBE bench to support benchmarking with a list of devices and speclist, making it more flexible and efficient for testing and optimizing TBE performance. Reviewed By: spcyppt Differential Revision: D78390216
kudomcho
force-pushed
the
mi350_dev_0919
branch
from
f726512 to
ddb47b4
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
5% uplift from B200
28% uplift from MI350