Adding MoE, PEE, GGEMM then SALM, vLLM related changes - #16038
Conversation
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> Signed-off-by: Taejin Park <tango4j@gmail.com>
…ith 'import' and 'import from'' Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> Signed-off-by: Taejin Park <tango4j@gmail.com>
|
/ok to test 025605c |
| @@ -0,0 +1,825 @@ | |||
| # Copyright (c) 2026, NVIDIA CORPORATION. All rights reserved. | |||
There was a problem hiding this comment.
This file should live in tests/collections/asr right?
| # per-encoder (see ParallelExpertEncoder.set_activation_checkpointing). Kept as a | ||
| # flag rather than a checkpoint_wrapper around each layer so module structure and | ||
| # state_dict keys stay identical to a checkpoint saved without it. | ||
| self.activation_checkpointing = False |
There was a problem hiding this comment.
Is this change necessary? Our training worked so far with AC and without this workaround.
There was a problem hiding this comment.
All the changes in Transformer Encoder are removed. Transformer encoder file is untouched.
…mport Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
|
/ok to test dab3466 |
…ith 'import' and 'import from'' Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> Signed-off-by: Taejin Park <tango4j@gmail.com>
…mport Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
7033beb to
23028a3
Compare
|
/ok to test 23028a3 |
|
[🤖]: Hi @tango4j 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully. So it might be time to merge this PR or get some approvals. |
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
Signed-off-by: Taejin Park <tango4j@gmail.com>
|
/ok to test aa368b3 |
|
[🤖]: Hi @tango4j 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully. So it might be time to merge this PR or get some approvals. |
Important
The
Update branchbutton must only be pressed in very rare occasions.An outdated branch is never blocking the merge of a PR.
Please reach out to the automation team before pressing that button.
What does this PR do?
Adds grouped-GEMM Mixture-of-Experts (MoE) and Parallel Expert Encoder (PEE) support to ASR, and integrates PEE with SpeechLM2 SALM training and generation.
Collection: ASR, SpeechLM2
Changelog
GGEMMTransformerEncoderfor packed execution of heterogeneous transformer experts, including grouped attention and feed-forward paths with serial reference implementations for correctness checks.MoETransformerEncoderwith dense and top-k expert routing plus activation-checkpointing support.ParallelExpertEncoder, combining speech MoE, speaker Sortformer, and sound experts behind a Conformer-compatible interface.model.pe_encoder_path, including external speaker-target routing, speaker-target lengths through context-parallel/chunked batches, and generation-only online inference.Usage
Configure a PEE bundle as the SALM perception encoder:
PEE automatically uses its memory-efficient per-expert path while training and its packed GGEMM path during evaluation and inference.
GitHub Actions CI
The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.
The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".
Before your PR is "Ready for review"
Pre checks:
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information
git diff --checkvalidation passed.