Show use torch.compile on TorchAO charts #6368
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
|
@huydhn is attempting to deploy a commit to the Meta Open Source Team on Vercel. A member of the Team first needs to authorize it. |
facebook-github-bot
added
the
CLA Signed
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
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Outdated suggestions cannot be applied.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.
Some data is missing on the chart otherwise. For example https://hud.pytorch.org/benchmark/llms?startTime=Thu%2C%2027%20Feb%202025%2001%3A12%3A08%20GMT&stopTime=Thu%2C%2006%20Mar%202025%2001%3A12%3A08%20GMT&granularity=day&lBranch=main&lCommit=6946094f6fe9ff77ca02736567ddf2fc031d5fd300ce7c60d832cf9c301c4c48&rBranch=main&rCommit=6946094f6fe9ff77ca02736567ddf2fc031d5fd300ce7c60d832cf9c301c4c48&repoName=pytorch%2Fao&benchmarkName=&modelName=AlbertForMaskedLM&backendName=&modeName=inference&dtypeName=autoquant&deviceName=cuda%20(NVIDIA%20H100)&archName=All%20Platforms shows only 0.99 on
compile v.s eager speedupchart, while it should include the other value (6.85)Preview
https://torchci-git-fork-huydhn-fix-ao-data-fbopensource.vercel.app/benchmark/llms?startTime=Thu%2C%2027%20Feb%202025%2001%3A12%3A08%20GMT&stopTime=Thu%2C%2006%20Mar%202025%2001%3A12%3A08%20GMT&granularity=day&lBranch=main&lCommit=6946094f6fe9ff77ca02736567ddf2fc031d5fd300ce7c60d832cf9c301c4c48&rBranch=main&rCommit=6946094f6fe9ff77ca02736567ddf2fc031d5fd300ce7c60d832cf9c301c4c48&repoName=pytorch%2Fao&benchmarkName=&modelName=AlbertForMaskedLM&backendName=&modeName=inference&dtypeName=autoquant&deviceName=cuda%20(NVIDIA%20H100)&archName=All%20Platforms shows up the missing value
@jerryzh168 I notice that there could be multiple records of the same model in the same commit, mostly from
noquanteager. For example,6946094f6fe9ff77ca02736567ddf2fc031d5fd300ce7c60d832cf9c301c4c48andAlbertForMaskedLMhas 1time_ms(avg)record forautoquant, 1time_ms(avg)record fornoquantusing torch.compile, but 5 of them fornoquanteager. Any thoughts?