--- name: ad-add-fusion-transformation-14c6b32521e0 description: > Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout. Prefer existing kernels and custom ops; use Triton only when no viable existing-kernel path exists. Use ad-graph-dump for AD_DUMP_GRAPHS_DIR workflows. Covers TRT-LLM paths, registry, default.yaml registration, graph validation, tests, and a review checklist — without prescribing profiling tools or throughput targets. license: Apache-2.0 tags: - tensorrt-llm - autodeploy - fusion - graph-transform - optimization metadata: author: NVIDIA Corporation --- # Autodeploy: Add Fusion Transformation Pass ## Where this skill applies This file lives in the **trtllm-agent-toolkit** plugin. Paths such as `tensorrt_llm/...`, `examples/auto_deploy/...`, and `tests/...` are relative to a **TensorRT-LLM source checkout** on the user’s machine — not the plugin tree. After installing the plugin (see the toolkit `README.md`), skills use the `trtllm-agent-toolkit:` prefix (for example `trtllm-agent-toolkit:ad-add-fusion-transformation`). ## Related skills in this plugin | Skill | Use it for | |-------|------------| | **ad-graph-dump** | Enabling `AD_DUMP_GRAPHS_DIR`, dump file layout, and how to read SSA graph output. | | **trtllm-codebase-exploration** | Mapping existing transforms, custom ops, and search patterns before writing a pass. | | **trtllm-code-contribution** | TensorRT-LLM pre-commit, tests, DCO sign-off, and PR expectations. | | **triton-kernel-writing** | Implementing a **Triton** op only after existing-kernel lookup fails. | | **triton-tileir-optimization** | Tuning **existing** Triton kernels for the TileIR backend when that path applies. | Use this skill when you already know **which subgraph or pattern** you are targeting (from graph dumps, logs, or code reading). For dump capture and file semantics, follow **ad-graph-dump** first. ## When to use this skill - Adding, extending, or reviewing a fusion under AutoDeploy transforms in a TensorRT-LLM tree. ### Workflow (concise) 1. Confirm the pattern in **current** graph dumps (see **ad-graph-dump**). 2. Search for an existing kernel or custom-op path before new Triton or CUDA. 3. Implement the smallest change that proves correctness and matching; add tests. 4. Re-run dumps and tests; if outputs drift, separate matching issues from metadata loss from numeric differences. ## Finding fusion candidates (lightweight) Do this before writing a new pass so you work on real graph structure. ### Inputs - Graph dump directory from a run with `AD_DUMP_GRAPHS_DIR` set (see **ad-graph-dump**). - Model id and active AutoDeploy config (registry YAML, `default.yaml` overlays). - TensorRT-LLM source tree for kernel and transform lookup. ### Outputs - Ordered list of candidates with: graph evidence, existing-kernel lookup (`found` / `not_found`), recommendation (`use_existing_kernel`, `needs_triton_fallback`, `defer`), and trade-offs (complexity, correctness risk). ### Discovery workflow 1. Parse dumps for repeated unfused patterns (element-wise chains, norm chains, epilogues, attention-adjacent ops). 2. Search the tree for equivalent transforms or custom ops; record file/symbol evidence. 3. If nothing fits, mark Triton or other kernel work as a deliberate fallback. 4. Prefer candidates with clear recurrence, existing support, and lower numerical risk. ### Per-candidate template ```text Candidate: Affected graph pattern: Existing kernel lookup: Evidence: Recommendation: Strengths / weaknesses / risks: - ... ``` ### Guardrails - Do not skip existing-kernel lookup. - Do not default to Triton when a viable existing op already exists. - If uncertain, `defer` and narrow the question with one more dump or test. --- ## Inputs (implementation) - Chosen candidate or concrete subgraph. - Active model and config files. - Fresh graph dumps when available. - Current baseline: match counts from logs, unit test status, any accuracy notes you already maintain. ## Outputs (implementation) - Pass design or patch: registered transform, `default.yaml` entry, optional model-registry YAML. - Path decision: `existing_kernel_path` vs `triton_fallback_path` (or other kernel stack). - Validation notes: graph evidence, `[SUMMARY] matches=...` before/after from AutoDeploy logs, test results. ## Implementation workflow 1. Align the pass with **observed** graph structure from dumps — not assumed op names from docs alone. 2. Search `transform/library/`, `custom_ops/`, `torch.ops.auto_deploy.*`, and related tests for reuse. 3. Integrate an existing op when possible; otherwise delegate kernel work to the appropriate skill (**triton-kernel-writing**, **cuda-kernel-writing**, etc.). 4. Keep one logical change per patch; extend tests in the same change. 5. Re-read dumps after the change; if match counts collapse, suspect pattern availability or metadata propagation. ## Where fusion passes live - Transforms: `tensorrt_llm/_torch/auto_deploy/transform/library/` - Registry / base behavior: `tensorrt_llm/_torch/auto_deploy/transform/interface.py` - Default transform list: `tensorrt_llm/_torch/auto_deploy/config/default.yaml` - Dump helper: `tensorrt_llm/_torch/auto_deploy/utils/graph_writer.py` - Graph utilities: `tensorrt_llm/_torch/auto_deploy/utils/node_utils.py`, `tensorrt_llm/_torch/auto_deploy/utils/_graph.py` - Custom ops: `tensorrt_llm/_torch/auto_deploy/custom_ops/` Tests (typical): - `tests/unittest/auto_deploy/singlegpu/transformations/library/` - `tests/integration/defs/accuracy/test_llm_api_autodeploy.py` (when behavior or numerics may change) ## How to add a transform ### Implement the pass Create or update a module under `transform/library/` and register the class: ```python @TransformRegistry.register("my_transform_key") class MyTransform(BaseTransform): @classmethod def get_config_class(cls): return MyTransformConfig ``` Use a dedicated config class only when the pass needs parameters beyond the base transform config. ### Register in `default.yaml` Add a key under `transforms:` in `tensorrt_llm/_torch/auto_deploy/config/default.yaml`. **Copy the field set from the closest existing transform** in the same section of the file (required keys depend on the transform config class and on how peers are declared). New experimental passes should stay **`enabled: false`** until covered by tests and dumps. ### Enable for a specific model For targeted rollout, adjust registry YAMLs under `examples/auto_deploy/model_registry/configs/` rather than turning on unproven passes globally. ## Implementation rules - Prefer existing AutoDeploy / TRT-LLM ops and `torch.ops.auto_deploy` entries. - Prefer stable, backend-neutral graph contracts; avoid hiding real dataflow in `node.meta` when an edge should carry it. - Use metadata for observable tensor facts (shape, dtype) and preserve it across rewrites when replacements should remain traceable. - **One hypothesis per patch** — do not mix unrelated fusions. ## Existing kernel first, Triton second Before Triton: 1. Search `transform/library/` and `custom_ops/`. 2. Search `torch.ops.auto_deploy.*` and TRT-LLM custom op definitions. 3. Read tests for similar integrations. Use **triton-kernel-writing** only when no suitable op exists and you accept owning kernel + integration work. ## Validation order 1. Graph dumps — pattern present, rewrite visible (see **ad-graph-dump**). 2. Unit tests for the transform. 3. Integration or accuracy checks when numerics or end-to-end behavior may change. ## Match counts AutoDeploy logs `[SUMMARY] matches=` (or `skipped` / `disabled`) per transform. Compare before and after your change; a large drop usually indicates pattern or metadata issues, not “slow runs.” ## Testing expectations Follow **trtllm-code-contribution** for repo conventions. Cover: - Happy-path micrograph or exported-graph rewrites. - Failure modes that must **not** fuse (multiple consumers, mixed consumers). - Metadata preservation when an upstream pass feeds your pattern. Primary unittest location for library transforms: - `tests/unittest/auto_deploy/singlegpu/transformations/library/` ## Review checklist - Target structure appears in current dumps. - Transform registered and listed in `default.yaml` consistently with peer entries. - Model-registry toggles are intentional. - Non-zero `matches` where expected, or `skipped` is explained. - Before/after dump snippets or diffs saved for the review thread. - Tests cover both success and intentional non-match cases. - If outputs change, classify match loss vs metadata loss vs acceptable numeric drift. ## Guardrails - Do not bundle unrelated passes in one change. - If dumps contradict expectations, document what you observed before chasing unrelated hypotheses. ## Iteration note (template) ```text Candidate: Path: Rationale: - ... Graph validation: Summary logs: Tests: Open risks: - ... ``` --- Source attribution: yo-steven Original project: https://github.com/yo-steven/skills-exploration-20260522/blob/6e1127ffb7690aa8038b172d0ae7cc720754870d/skills/TensorRT-LLM/ad-add-fusion-transformation/SKILL.md License: Apache-2.0 License information: https://www.apache.org/licenses/LICENSE-2.0 Original upstream instructions; downloaded from Dave AI. ## Upstream license notice SPDX-License-Identifier: Apache-2.0 AND CC-BY-4.0 Copyright (c) 2026 NVIDIA Corporation This project is licensed under a dual license: - Apache License 2.0 (for code and configuration) - Creative Commons Attribution 4.0 International (CC BY 4.0) (for documentation) You may use the contents of this repository under the terms of either license, or both, as applicable to the type of content. ================================================================================ Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. "Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to the Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by the Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding any notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS ================================================================================ Creative Commons Attribution 4.0 International License (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/ You are free to: Share — copy and redistribute the material in any medium or format for any purpose, even commercially. Adapt — remix, transform, and build upon the material for any purpose, even commercially. The licensor cannot revoke these freedoms as long as you follow the license terms. Under the following terms: Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits. Notices: You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation. No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material. For the full legal text, see: https://creativecommons.org/licenses/by/4.0/legalcode # Dave AI resource metadata Creator / publisher: yo-steven Original project: https://github.com/yo-steven/skills-exploration-20260522/blob/6e1127ffb7690aa8038b172d0ae7cc720754870d/skills/TensorRT-LLM/ad-add-fusion-transformation/SKILL.md Attribution basis: Source repository record Fields of work: Development & Engineering Roles: Backend Developer, Data Engineer, ML / AI Engineer Specialties: API, Backend Tools: Tensorrt Llm, Triton Country applicability: Country not specified Classification basis: Source catalog labels Instruction SHA-256: 45180a80159af66470ba22958f169b2ba077674f9aec3a609fc6bdf57d8a23ab