[#7222][autodeploy] Separate run_shape_prop as another graph utility #7313
Conversation
📝 WalkthroughWalkthroughDecouples shape propagation from canonicalization: interface now imports and calls run_shape_prop(gm) instead of canonicalize_graph(..., shape_prop=True). transformations/_graph.py splits canonicalize_graph and shape propagation into separate functions, adds run_shape_prop, and updates internal signatures/returns. Changes
Sequence Diagram(s)sequenceDiagram
participant Caller
participant Interface as transform.interface
participant Graph as transformations._graph
Caller->>Interface: _run_pre_cleanup(gm, ...)
Interface->>Graph: canonicalize_graph(gm)
alt requires_shape_prop and shapes invalid
Interface->>Graph: run_shape_prop(gm)
end
Interface-->>Caller: return
Caller->>Interface: _run_post_cleanup(gm, ...)
alt run_shape_prop enabled and shapes invalid
Interface->>Graph: run_shape_prop(gm)
end
Interface-->>Caller: return
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Suggested reviewers
✨ Finishing Touches
🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
Fridah-nv
force-pushed
the
user/fridah/move-sp
branch
from
54fd699 to
21ed2ae
Compare
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
tensorrt_llm/_torch/auto_deploy/transformations/_graph.py (2)
1-1: Add NVIDIA 2025 copyright header at file top.Required by repo guidelines; place before the module docstring.
Apply this diff:
+# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved. + """Graph-related utilities for transformations."""
157-169: Fix incorrect return annotation for _canonicalize_single_gm.Function mutates in-place and does not return a value.
Apply this diff:
-def _canonicalize_single_gm(gm: GraphModule) -> GraphModule: +def _canonicalize_single_gm(gm: GraphModule) -> None:
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (2)
tensorrt_llm/_torch/auto_deploy/transform/interface.py(3 hunks)tensorrt_llm/_torch/auto_deploy/transformations/_graph.py(2 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- tensorrt_llm/_torch/auto_deploy/transform/interface.py
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Code must target Python 3.8+
Indent Python code with 4 spaces; do not use tabs
Preserve module namespaces when importing; import modules/packages and access members via the module (e.g., from package.subpackage import foo; foo.SomeClass())
Python file names should be snake_case
Python class names should be PascalCase
Python functions/methods and local variables should be snake_case; variables beginning with a number should be prefixed with k_ (e.g., k_99th_percentile)
Global variables should be UPPER_SNAKE_CASE prefixed with G_ (e.g., G_MY_GLOBAL); constants should be UPPER_SNAKE_CASE
Avoid shadowing variables from outer scopes; initialize all externally visible members in init
Prefer docstrings for interfaces used outside a file; comments should be reserved for in-function or file-local interfaces
Use Google-style docstrings for classes and functions; attributes and variables may be documented inline with trailing string literals
Avoid reflection when simpler, explicit code suffices (e.g., avoid dict(**locals()) patterns)
In try/except, catch the narrowest exceptions possible
For duck-typing patterns, keep the try body minimal and move logic to else to avoid masking unrelated failures
Files:
tensorrt_llm/_torch/auto_deploy/transformations/_graph.py
**/*.{c,cc,cpp,cxx,h,hh,hpp,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend the NVIDIA copyright header (current year) to all source files (.cpp, .h, .cu, .py, etc.)
Files:
tensorrt_llm/_torch/auto_deploy/transformations/_graph.py
🧬 Code graph analysis (1)
tensorrt_llm/_torch/auto_deploy/transformations/_graph.py (1)
tensorrt_llm/logger.py (2)
debug(143-144)warning(131-132)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Pre-commit Check
🔇 Additional comments (3)
tensorrt_llm/_torch/auto_deploy/transformations/_graph.py (3)
214-240: Separation of shape propagation looks good.API is clear, logs before/after, and submodules are handled in reverse order; passing args only at top-level is sensible.
171-185: canonicalize_graph docstring updated and call sites verifiedThe docstring has been revised to reflect that
canonicalize_graphoperates in-place and returnsNone. A search across the codebase confirms that all invocations (intransform/interface.py,transform/library/quantization.py, andexport/export.py) callcanonicalize_graph(gm)without assigning or returning its result, so no further changes are needed.
132-140: Add missing return inmove_to_device
The function is annotated to return anfx.GraphModulebut currently falls through and returnsNone. Call sites ignore the return value (so adding a return is non-breaking) and it’s more ergonomic to return the module for potential chaining.• File:
tensorrt_llm/_torch/auto_deploy/transformations/_graph.py
• Location: end ofmove_to_device(after the for-loop)Apply this diff:
def move_to_device(gm: fx.GraphModule, device: DeviceLikeType) -> fx.GraphModule: @@ for _, subgm in reversed(list(named_graphmodules(gm))): # recompile graph to update self generated codes in subgraph _move_single_gm_to_device(subgm, device) + + return gm
Fridah-nv
force-pushed
the
user/fridah/move-sp
branch
from
21ed2ae to
49ed3a6
Compare
|
/bot run |
|
PR_Github #17419 [ run ] triggered by Bot |
|
PR_Github #17419 [ run ] completed with state |
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com> update docstring Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
Fridah-nv
force-pushed
the
user/fridah/move-sp
branch
from
a6e6318 to
0e5c65f
Compare
|
/bot run |
|
PR_Github #17430 [ run ] triggered by Bot |
|
PR_Github #17430 [ run ] completed with state |
|
/bot run |
|
PR_Github #17551 [ run ] triggered by Bot |
|
PR_Github #17551 [ run ] completed with state |
…ility (NVIDIA#7313) Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
4 participants
Summary by CodeRabbit
New Features
Refactor
Developer Impact
Description
Test Coverage
GitHub Bot Help
/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...Provide a user friendly way for developers to interact with a Jenkins server.
Run
/bot [-h|--help]to print this help message.See details below for each supported subcommand.
run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]Launch build/test pipelines. All previously running jobs will be killed.
--reuse-test (optional)pipeline-id(OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.--disable-reuse-test(OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.--disable-fail-fast(OPTIONAL) : Disable fail fast on build/tests/infra failures.--skip-test(OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.--stage-list "A10-PyTorch-1, xxx"(OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.--gpu-type "A30, H100_PCIe"(OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.--test-backend "pytorch, cpp"(OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.--only-multi-gpu-test(OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.--disable-multi-gpu-test(OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.--add-multi-gpu-test(OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.--post-merge(OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx"(OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".--detailed-log(OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.--debug(OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in thestage-listparameter to access the appropriate container environment. Note: Does NOT update GitHub check status.For guidance on mapping tests to stage names, see
docs/source/reference/ci-overview.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip testing for latest commit on pull request.
--comment "Reason for skipping build/test"is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.reuse-pipeline
reuse-pipelineReuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.