Add vLLM grouped gemm backend for MoE inference#4566
Open
santhnm2 wants to merge 98 commits intoNVIDIA:mainfrom
Open
Add vLLM grouped gemm backend for MoE inference#4566santhnm2 wants to merge 98 commits intoNVIDIA:mainfrom
santhnm2 wants to merge 98 commits intoNVIDIA:mainfrom
Conversation
- Fix NCCLAllGatherDispatcher.set_step_metadata writing _valid_tokens_tensor to the subclass instead of InferenceAllGatherDispatcherBase, causing the Triton kernel to receive None and crash with 'constexpr has no attr is_ptr' - Add use_allgather_v support to NCCLAllGatherDispatcher: non-CG steps (prefill) all-gather actual per-rank token counts, pad to max, AllGather, compact on dispatch; expand, ReduceScatter, truncate on combine - Context passes use_allgather_v=not using_cuda_graph_this_step() for NCCL; both context and wrapper now all-gather actual per-rank counts rather than trivially filling (dummy forward always eager → use_allgather_v=True) - Fix using_cuda_graph_this_step missing parentheses (property → method call)
Signed-off-by: Keshav Santhanam <ksanthanam@nvidia.com>
Signed-off-by: Keshav Santhanam <ksanthanam@nvidia.com>
Signed-off-by: Keshav Santhanam <ksanthanam@nvidia.com>
Signed-off-by: Keshav Santhanam <ksanthanam@nvidia.com>
Signed-off-by: Keshav Santhanam <ksanthanam@nvidia.com>
Signed-off-by: Keshav Santhanam <ksanthanam@nvidia.com>
Contributor
Author
|
/ok to test c49de0c |
kvareddy
approved these changes
May 1, 2026
Contributor
Author
|
/ok to test f04ad51 |
Victarry
approved these changes
May 1, 2026
ericharper
approved these changes
May 1, 2026
svcnvidia-nemo-ci
added
Approved
shanmugamr1992
approved these changes
May 1, 2026
Contributor
Author
|
/ok to test 4a034a8 |
Signed-off-by: Keshav Santhanam <ksanthanam@nvidia.com>
Contributor
Author
|
/ok to test e7840c9 |
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
7 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.
What does this PR do ?
Ports the vLLM grouped gemm kernel to the inference-optimized MoE backend.
Issue tracking
For PRs from open-source community contributors:
Linked issue:
Contribution process
Pre-checks
Code review
Feel free to message or comment the @mcore-oncall to help accelerate your merge into main. The less complex your PR is, the faster it will be approved and merged!
All PRs start as draft. If you open a non-draft PR, it will be automatically converted to draft.
Step 1: Mark PR as "Ready for Review"
.github/CODEOWNERS.Final Review might get declined if these requirements are not fulfilled.
Step 2: Final Review
For PRs that change
megatron/core, once all expert reviewers have approved, theFinal Reviewlabel is applied automatically and final reviewers are assigned.For PRs outside
megatron/core, this step is skipped.Step 3: Approved
Once all required reviewers have approved, the
Approvedlabel is applied automatically.Merge
Any member of mcore-engineers will be able to merge your PR.
For MRs into `dev` branch
The proposed review process for `dev` branch is under active discussion.MRs are mergable after one approval by either
eharper@nvidia.comorzijiey@nvidia.com.