[main] feat(moe): Support gated delta net for Qwen3-Next (1/4)

[yuzhongw-nvidia]

What does this PR do ?

MR to dev.

Design doc

Qwen3-Next functionality PRs.

• [main] feat(moe): Support moe shared expert gate for Qwen3-Next (2/4) #2751
• [main] feat(moe): Support attention output gate for Qwen3-Next (3/4) #2752
• [main] feat(moe): Support apply wd to qk layernorm for Qwen3-Next (4/4) #2753

Changes in this PR:

1. Gated Delta Net (GDN);
2. num_floating_point_operations

New supported arguments for Qwen3-Next

--attention-output-gate: true  # Qwen3-Next applies output gate to standard attention layers
--no-weight-decay-cond-type: qwen3_next  # Qwen3-Next applies weight decay to qk layernorm as a special case
--moe-shared-expert-gate: true  # Qwen3-Next have a shared expert gate
# GDN args
--linear-attention-type: gated_delta_net
--linear-attention-freq: 4  # 1 1 1 0 1 1 1 0 ..., or we can use ([1,1,1,0]*12) to represent
--linear-conv-kernel-dim: 4
--linear-key-head-dim: 128
--linear-value-head-dim: 128
--linear-num-key-heads: 16
--linear-num-value-heads: 32

New for Qwen3-Next, but already supported in MCore yet

--rotary-percent: 0.25  # Qwen3-Next applies RoPE only to the first 25% of position dimensions
--rotary-base: 10000000  # Qwen3-Next uses a larger rotary base
--apply-layernorm-1p: true  # Zero-Centered RMSNorm for Qwen3-Next
--max-position-embeddings: 262144  # Qwen3-Next-80B-A3B supports up to 256k sequence length
--moe-shared-expert-intermediate-size: 512  # Qwen3-Next have a shared expert
# MTP: Qwen3-Next has one MTP layer
--mtp-num-layers: 1
--mtp-loss-scaling-factor: 0.1

LM loss curve with the training dataset of Qwen3 are as below (GBS=256, seq_len=4096, TP1 is in green, TP2 is in blue).

wandb url

⚠️ For major changes (either in lines of code or in its impact), please make sure to first share discuss a design-doc with the team.

Contribution process

flowchart LR
    A[Pre-checks] --> B[PR Tests]
    subgraph Code Review/Approval
        C1[Expert Review] --> C2[Final Review]
    end
    B --> C1
    C2 --> D[Merge]

Loading

Pre-checks

• I want this PR in a versioned release and have added the appropriate Milestone (e.g., Core 0.8)
• I have added relevant unit tests
• I have added relevant functional tests
• I have added proper typing to my code Typing guidelines
• I have added relevant documentation
• I have run the autoformatter.sh on my PR

Code review

The following process is enforced via the CODEOWNERS file for changes into megatron/core. For changes outside of megatron/core, it is up to the PR author whether or not to tag the Final Reviewer team.

For MRs into `main` branch

(Step 1): Add PR label Expert Review

(Step 2): Collect the expert reviewers reviews

1. Attach the Expert Review label when your PR is ready for review.
2. GitHub auto-assigns expert reviewers based on your changes. They will get notified and pick up your PR soon.

⚠️ Only proceed to the next step once all reviewers have approved, merge-conflict are resolved and the CI is passing.
Final Review might get declined if these requirements are not fulfilled.

(Step 3): Final Review

1. Add Final Review label
2. GitHub auto-assigns final reviewers based on your changes. They will get notified and pick up your PR soon.

(Optional Step 4): Cherry-pick into release branch

If this PR also needs to be merged into core_r* release branches, after this PR has been merged, select Cherry-pick to open a new PR into the release branch.

For MRs into `dev` branch

The proposed review process for `dev` branch is under active discussion.

MRs are mergable after one approval by either [email protected] or [email protected].

Merging your PR

Any member of core-adlr and core-nemo will be able to merge your PR.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[jaredcasper]

What tests have been done to validate the implementation of the gated delta net is correct?

[yuzhongw-nvidia]

Hi @jaredcasper , I have rebased main and make the following changes to this MR,

1. Resolve [main] feat(moe): Support gated delta net for Qwen3-Next (1/4) #1989 (comment)
2. Try to make Attention.get_query_key_value_tensors clear. Does it look better now?

Thanks. cc @yanring

[yuzhongw-nvidia]

What tests have been done to validate the implementation of the gated delta net is correct?

Hi @jaredcasper , we have do several things to validate the implementation.

1. We have a UT to verify the implementation of GDN and parallel GDN.
2. We have used the comparing tool in Megatron-Bridge to verify the alignment with HF implementation.
3. We have run a E2E training test and see the loss curve makes sense. (wandb)

In the next few weeks, we will further add a functional test to guarantee the long-term correctness of Qwen3-Next.

[jaredcasper]

In the next few weeks, we will further add a functional test to guarantee the long-term correctness of Qwen3-Next.

In the meantime do you think it makes sense to split this up and get the other features in?

[yuzhongw-nvidia]

In the next few weeks, we will further add a functional test to guarantee the long-term correctness of Qwen3-Next.

In the meantime do you think it makes sense to split this up and get the other features in?

Do you mean covering multiple features in a single functional test? It will be excellent, as long as we do not have too many features in one test case making it hard to maintain.

[yuzhongw-nvidia]

Hi @jaredcasper , I remember you mentioned that you need a thorough review to the gpt_layer_spec.py. Do you have any comments or feedback about it? Does it look good, or do you think we need to refine it?

[jaredcasper]

Do you mean covering multiple features in a single functional test? It will be excellent, as long as we do not have too many features in one test case making it hard to maintain.

No, I mean there are 7 changes listed in the PR, do they all need to be in one PR? I'm saying while some of the features are getting tests added for them does it make sense to open PRs for some of the others that have been tested.

[jaredcasper]

Hi @jaredcasper , I remember you mentioned that you need a thorough review to the gpt_layer_spec.py. Do you have any comments or feedback about it? Does it look good, or do you think we need to refine it?

I thought you were going to work on it a bit after our conversation, but if you are done refining I've asked some from my team to do a thorough review.

[yuzhongw-nvidia]

/ok to test f58c310