Add flop calculation for custom Qwen 3 model#3759
Merged
copybara-service[bot] merged 1 commit intomainfrom Apr 28, 2026
Merged
Conversation
NuojCheng
approved these changes
Apr 28, 2026
gobbleturk
approved these changes
Apr 28, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds a
QWEN3_CUSTOM_MOEbranch to the FLOPs calculator that accounts for the compressedmoe_expert_input_dim/attention_output_dim(768) used by the FFN/gate and attention projection, plus the per-layer up-projection back toemb_dim.Tests
test_qwen3_custom_30b_a3b_flopsvalidates against the 6·N·Dheuristic (~2.86B active params)
Checklist
Before submitting this PR, please make sure (put X in square brackets):
gemini-reviewlabel.