NVIDIA-Nemotron-Nano-12B-v2 support #147
Merged
Conversation
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
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
There was a problem hiding this comment.
Pull Request Overview
This PR adds support for the NVIDIA-Nemotron-Nano-12B-v2 model to the TensorRT-LLM auto deploy system.
- Introduces model-specific patches for Nemotron-H architecture including RMS norm implementations and forward pass modifications
- Adds configuration and test support for the new model in testing infrastructure
- Improves attention pattern matching to handle additional grouped attention patterns
- Fixes scale validation logic in attention custom ops to properly handle None values
Reviewed Changes
Copilot reviewed 8 out of 8 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
tensorrt_llm/_torch/auto_deploy/models/patches/nemotron_h.py |
New patch file implementing Nemotron-H specific model modifications and RMS norm replacement |
tests/unittest/_torch/auto_deploy/_utils_test/_model_test_utils.py |
Adds test configuration for NVIDIA-Nemotron-Nano-12B-v2 model |
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_build_small_single.py |
Integrates new model into build tests with transformers mode skip |
tests/unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.py |
Parameterizes hybrid patch tests to include Nemotron model |
tensorrt_llm/_torch/auto_deploy/transform/library/attention.py |
Adds new grouped attention pattern matching for additional attention configurations |
tensorrt_llm/_torch/auto_deploy/custom_ops/*.py |
Fixes scale validation to properly handle None values in attention operations |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_build_small_single.py
Show resolved
Hide resolved
lucaslie
commented
Sep 27, 2025
lucaslie
commented
Sep 27, 2025
tests/unittest/_torch/auto_deploy/unit/singlegpu/models/test_hybrid_patches.py
Show resolved
Hide resolved
nvchenghaoz
approved these changes
Sep 27, 2025
1 task
lucaslie
added a commit
that referenced
this pull request
Sep 29, 2025
* [None][feat] Add patches for NemotronH Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> * [None][test] unittest for nemotron_h Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> * nemotron-h support finished Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> * added anticapted path for new models on llm_models trt-llm CI Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> --------- Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> Co-authored-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
nvchenghaoz
pushed a commit
that referenced
this pull request
Oct 1, 2025
* [None][feat] Add patches for NemotronH Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> * [None][test] unittest for nemotron_h Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> * nemotron-h support finished Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> * added anticapted path for new models on llm_models trt-llm CI Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> --------- Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> Co-authored-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
nvchenghaoz
pushed a commit
that referenced
this pull request
Oct 3, 2025
* [None][feat] Add patches for NemotronH Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> * [None][test] unittest for nemotron_h Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> * nemotron-h support finished Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> * added anticapted path for new models on llm_models trt-llm CI Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> --------- Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com> Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com> Co-authored-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
see title
config.yamltorch-opt+trtllm