Conversation
merceod
force-pushed
the
engine/dense-parallel-mlp
branch
from
September 23, 2026 23:14
4ab7255 to
8649b5a
Compare
This branch has not been deployed
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Small shared component for the dense (ungated) FFN used by the Nemotron family.
ParallelMLP=down_proj(act(up_proj(x))), withup_projcolumn-parallel anddown_projrow-parallel. Parameter names follow the dense-LLM checkpoint convention so a Nemotron-style FFN loads by name._resolve_activationnow knowsrelu2/relu_squared.ParallelGatedMLPUnfused.First user is the Cosmos3-Edge integration (#297), whose DiT and reasoner share a dense Nemotron backbone with
hidden_act=relu2. Nemotron-H based models can reuse it.Tests in
test/modular/test_parallel_mlp.py(CPU) cover relu2 semantics, state_dict names and shapes, and parity with annn.functionalreference for relu2 and gelu+bias.ruffandtest/modularpass.