Report MFU on B300 in VLMTokensPerSec#114
Open
main-voice wants to merge 1 commit into
Open
Conversation
torch.cuda.get_device_name() returns 'NVIDIA B300 SXM6 AC', which the
device->peak-FLOPs table in VLMTokensPerSec._resolve_peak_flops did not
match, so useful_mfu was skipped ("unknown device ... MFU not reported").
Add a B300/GB300 branch returning 2.25e15 (HGX B300 dense BF16 per the
NVIDIA datasheet: 36 PFLOPS sparse / 2 / 8 GPUs = 2.25 PFLOP/s/GPU),
placed ahead of the B200 branch since the peaks differ.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
torch.cuda.get_device_name() returns 'NVIDIA B300 SXM6 AC', which the device->peak-FLOPs table in VLMTokensPerSec._resolve_peak_flops did not match, so useful_mfu was skipped ("unknown device ... MFU not reported").
Add a B300/GB300 branch returning 2.25e15 (HGX B300 dense BF16 per the NVIDIA datasheet: 36 PFLOPS sparse / 2 / 8 GPUs = 2.25 PFLOP/s/GPU), placed ahead of the B200 branch since the peaks differ.