-
Notifications
You must be signed in to change notification settings - Fork 56
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.
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
[Profiling] Model and device specific folders for profiled data, documentation for profiling #7
Merged
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
nitinkedia7
approved these changes
May 12, 2024
…into users/amey/arxiv_update
…into users/amey/arxiv_update
nitinkedia7
changed the title
Update readme
Model and device specific folders for profiled data, documentation for profiling
May 14, 2024
nitinkedia7
changed the title
Model and device specific folders for profiled data, documentation for profiling
[Profiling] Model and device specific folders for profiled data, documentation for profiling
May 14, 2024
Hanchenli
pushed a commit
to XbzOnGit/vidur
that referenced
this pull request
Nov 8, 2024
…mentation for profiling (microsoft#7) * minor * minor * minor * minor * profiling refactoring * minor * various fixes * minor * minor * minor * Fix CUDA illegal memory encountered error * minor * minor * Do not have hardcoded num_blocks * h100 mlp * h100 mlp * h100 mlp+attention+ar * Add A100 compute data in new format * Fix mlp profiling * Document how to add a new model * Fix incomplete mlp data for a100, delete for H100 (need reprofiling) * Change paths for profiling data files * format * Add highlight figures in README --------- Co-authored-by: Amey Agrawal <[email protected]> Co-authored-by: Nitin Kedia <[email protected]> Co-authored-by: Ubuntu <azureuser@vmss000005.qcze0vdp4tsupb4kdsslztcwbe.gvxx.internal.cloudapp.net>
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.
Description
This PR changes the structure for profiling data with the aim to make adding a new model, device follow a Bring Your Own File model. The new structure is described here. Several bugs also have been fixed, notably removed hard-coded number of blocks in attention profiling.
Test Plan
The entire profiling data is new, so it was a real test 🧪 of running all the profiling scripts.
Also, verified fidelity for
34b
model onarxiv
trace with bothvllm
andsarathi
schedulers.Next steps
cpu_overhead
profiling data for all models.