New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Improve speedup display for TorchAO dashboard #6176

Open

huydhn opened this issue Jan 15, 2025 · 0 comments

Assignees

Contributor

huydhn commented Jan 15, 2025 •

edited

Loading

There are several requests for TorchAO dashboard:

To show different speedups:
a. speedup autoquant + compile v.s compile (what the dashboard is currently showing)
b. ~~speedup compile v.s. eager~~ speedup autoquant v.s. eager
To be able to see the speedup between the base commit and the new commit like what we have in https://hud.pytorch.org/benchmark/compilers

cc @jerryzh168 @yangw-dev

huydhn self-assigned this

github-project-automation bot added this to PyTorch OSS Dev Infra

huydhn moved this to In Progress in PyTorch OSS Dev Infra

huydhn mentioned this issue

Add TorchAO speedup metric vs eager #6178

Merged

huydhn added a commit that referenced this issue


          Add TorchAO speedup metric vs eager (#6178)

cb2e2d9

Addresses the first part of
#6176

This PR adds another speedup metric vs eager. Because this is TorchAO
dashboard, I think it's more appropriate to show TorchAO vs compile and
TorchAO vs eager instead of TorchAO vs compile and compile vs eager
because the last one (compile vs eager) is a fit for PT2 inductor
dashboard instead. @jerryzh168 What do you think?

I also fix another UX issue to show the oldest commit in the time range
as the base commit instead.

### Testing


https://torchci-git-fork-huydhn-improve-ao-speedup-metric-fbopensource.vercel.app/benchmark/llms?startTime=Thu%2C%2009%20Jan%202025%2010%3A21%3A42%20GMT&stopTime=Thu%2C%2016%20Jan%202025%2010%3A21%3A42%20GMT&granularity=day&lBranch=main&lCommit=2cddc67fe700579043e3e2d395d983764298b82e9746e9b2663c583710b3b08c&rBranch=main&rCommit=399034112cd82562f0d651bda8a8b5ab8840703ee0b40cd136d85181164d2280&repoName=pytorch%2Fao&modelName=All%20Models&backendName=All%20Backends&dtypeName=All%20DType&deviceName=All%20Devices

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment