feat: add AMD Instinct peak FLOPS for MFU on ROCm#262
Open
Abhishek21g wants to merge 1 commit into
Open
Conversation
get_peak_flops() fell back to A100 for MI250/MI300, skewing MFU on ROCm hosts. Add published peak BF16/FP16 matrix FLOPS for MI100, MI210, MI250, and MI300 with unit tests. Complements PrimeIntellect-ai#255 (ROCm support).
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
get_peak_flops()only recognizes A100/H100. On ROCm hosts (MI250/MI300), MFU denominators default to A100 (312 TFLOPS) and reported utilization is wrong.Fix
Add published dense matrix BF16/FP16 peak FLOPS for MI100, MI210, MI250, and MI300 in
zeroband/utils/__init__.py.Complements #255 (ROCm support) — no overlap with training-path changes.
Verification