Add torchao to PT2 Benchmark Runner #2268
Closed
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
|
This pull request was exported from Phabricator. Differential Revision: D57463273 |
xuzhao9
added a commit
to xuzhao9/benchmark
that referenced
this pull request
May 16, 2024
Summary: Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Reviewed By: jerryzh168 Differential Revision: D57463273
|
This pull request was exported from Phabricator. Differential Revision: D57463273 |
xuzhao9
added a commit
to xuzhao9/benchmark
that referenced
this pull request
May 16, 2024
Summary: X-link: pytorch/pytorch#126469 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Reviewed By: jerryzh168 Differential Revision: D57463273
|
This pull request was exported from Phabricator. Differential Revision: D57463273 |
xuzhao9
added a commit
to xuzhao9/benchmark
that referenced
this pull request
May 16, 2024
Summary: X-link: pytorch/pytorch#126469 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Reviewed By: jerryzh168 Differential Revision: D57463273
xuzhao9
added a commit
to xuzhao9/pytorch
that referenced
this pull request
May 16, 2024
Summary: X-link: pytorch/benchmark#2268 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Test Plan: ``` $ buck2 run mode/opt //caffe2/benchmarks/dynamo:torchbench -- --only BERT_pytorch --bfloat16 --quantization int8dynamic --performance --inference --print-memory loading model: 0it [00:50, ?it/s] cuda eval BERT_pytorch memory: eager: 0.75 GB, dynamo: 0.75 GB, ratio: 1.00 running benchmark: 100% 1.003x ``` Reviewed By: jerryzh168 Differential Revision: D57463273
|
This pull request was exported from Phabricator. Differential Revision: D57463273 |
huydhn
approved these changes
May 16, 2024
xuzhao9
added a commit
to xuzhao9/benchmark
that referenced
this pull request
May 17, 2024
Summary: X-link: pytorch/pytorch#126469 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Reviewed By: jerryzh168 Differential Revision: D57463273
xuzhao9
added a commit
to xuzhao9/pytorch
that referenced
this pull request
May 17, 2024
Summary: X-link: pytorch/benchmark#2268 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Test Plan: ``` $ buck2 run mode/opt //caffe2/benchmarks/dynamo:torchbench -- --only BERT_pytorch --bfloat16 --quantization int8dynamic --performance --inference --print-memory loading model: 0it [00:50, ?it/s] cuda eval BERT_pytorch memory: eager: 0.75 GB, dynamo: 0.75 GB, ratio: 1.00 running benchmark: 100% 1.003x ``` Reviewed By: jerryzh168 Differential Revision: D57463273
xuzhao9
added a commit
to xuzhao9/benchmark
that referenced
this pull request
May 17, 2024
Summary: X-link: pytorch/pytorch#126469 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Reviewed By: jerryzh168 Differential Revision: D57463273
|
This pull request was exported from Phabricator. Differential Revision: D57463273 |
xuzhao9
had a problem deploying
to
docker-s3-upload
GitHub Actions
Failure
xuzhao9
added a commit
to xuzhao9/benchmark
that referenced
this pull request
May 18, 2024
Summary: X-link: pytorch/pytorch#126469 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Reviewed By: jerryzh168 Differential Revision: D57463273
xuzhao9
added a commit
to xuzhao9/pytorch
that referenced
this pull request
May 18, 2024
Summary: X-link: pytorch/benchmark#2268 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Test Plan: ``` $ buck2 run mode/opt //caffe2/benchmarks/dynamo:torchbench -- --only BERT_pytorch --bfloat16 --quantization int8dynamic --performance --inference --print-memory loading model: 0it [00:50, ?it/s] cuda eval BERT_pytorch memory: eager: 0.75 GB, dynamo: 0.75 GB, ratio: 1.00 running benchmark: 100% 1.003x ``` Reviewed By: jerryzh168 Differential Revision: D57463273
|
This pull request was exported from Phabricator. Differential Revision: D57463273 |
Summary: X-link: pytorch/pytorch#126469 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Reviewed By: jerryzh168 Differential Revision: D57463273
xuzhao9
added a commit
to xuzhao9/pytorch
that referenced
this pull request
May 18, 2024
Summary: X-link: pytorch/benchmark#2268 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Test Plan: ``` $ buck2 run mode/opt //caffe2/benchmarks/dynamo:torchbench -- --only BERT_pytorch --bfloat16 --quantization int8dynamic --performance --inference --print-memory loading model: 0it [00:50, ?it/s] cuda eval BERT_pytorch memory: eager: 0.75 GB, dynamo: 0.75 GB, ratio: 1.00 running benchmark: 100% 1.003x ``` Reviewed By: jerryzh168 Differential Revision: D57463273
|
This pull request was exported from Phabricator. Differential Revision: D57463273 |
xuzhao9
added a commit
to xuzhao9/pytorch
that referenced
this pull request
May 19, 2024
Summary: X-link: pytorch/benchmark#2268 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Test Plan: ``` $ buck2 run mode/opt //caffe2/benchmarks/dynamo:torchbench -- --only BERT_pytorch --bfloat16 --quantization int8dynamic --performance --inference --print-memory loading model: 0it [00:50, ?it/s] cuda eval BERT_pytorch memory: eager: 0.75 GB, dynamo: 0.75 GB, ratio: 1.00 running benchmark: 100% 1.003x ``` Differential Revision: D57463273 Pulled By: xuzhao9
facebook-github-bot
pushed a commit
that referenced
this pull request
May 20, 2024
Summary: X-link: #2268 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. X-link: pytorch/pytorch#126469 Reviewed By: jerryzh168 Differential Revision: D57463273 Pulled By: xuzhao9 fbshipit-source-id: 64520f18b63107ce5f07447ef7f4a8c841d9ff1f
pytorchmergebot
pushed a commit
to pytorch/pytorch
that referenced
this pull request
May 20, 2024
Summary: X-link: pytorch/benchmark#2268 Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline. Test Plan: ``` $ buck2 run mode/opt //caffe2/benchmarks/dynamo:torchbench -- --only BERT_pytorch --bfloat16 --quantization int8dynamic --performance --inference --print-memory loading model: 0it [00:50, ?it/s] cuda eval BERT_pytorch memory: eager: 0.75 GB, dynamo: 0.75 GB, ratio: 1.00 running benchmark: 100% 1.003x ``` Reviewed By: jerryzh168 Differential Revision: D57463273 Pull Request resolved: #126469 Approved by: https://github.com/huydhn
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.
Summary: Support torchao performance and accuracy tests in PT2 Benchmark Runner, using the inductor backend as the baseline.
Reviewed By: jerryzh168
Differential Revision: D57463273