[https://nvbugs/5454559][fix] handle bias term in fuse_gate_mlp #7449
Conversation
|
/bot run |
|
PR_Github #17244 [ run ] triggered by Bot |
|
PR_Github #17244 [ run ] completed with state |
|
/bot run |
|
PR_Github #17335 [ run ] triggered by Bot |
|
PR_Github #17335 [ run ] completed with state |
📝 WalkthroughWalkthroughUpdated FP8 quantization path in fuse_gate_mlp to set fused gate-mlp bias when present by concatenating mlp.gate.bias and mlp.fc.bias along axis 0, aligning with existing non-FP8 behavior. No signature changes; only Changes
Sequence Diagram(s)sequenceDiagram
participant C as Caller
participant MU as modeling_utils.fuse_gate_mlp
participant FL as fused_layer
Note over C,MU: Fuse gate+MLP
C->>MU: fuse_gate_mlp(mlp, quant_cfg=FP8, ...)
MU->>MU: Create fused_layer
MU->>FL: Assign fused weights (FP8)
alt FP8 path with bias present
MU->>MU: concat(gate.bias, fc.bias) along axis 0
MU->>FL: Set fused_fc.bias.value
else No bias
MU->>FL: Leave bias unset
end
MU-->>C: return fused_layer
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes ✨ 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
|
![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
🧹 Nitpick comments (1)
tensorrt_llm/models/modeling_utils.py (1)
1237-1237: Be explicit when checking for bias presence.If mlp.bias can be a Parameter, prefer
is not Noneto avoid truthiness quirks:if mlp.bias is not 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 (1)
tensorrt_llm/models/modeling_utils.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use only spaces, no tabs; indent with 4 spaces.
Files:
tensorrt_llm/models/modeling_utils.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.
Files:
tensorrt_llm/models/modeling_utils.py
**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).
Files:
tensorrt_llm/models/modeling_utils.py
🧠 Learnings (1)
📓 Common learnings
Learnt from: Fridah-nv
PR: NVIDIA/TensorRT-LLM#7227
File: tests/unittest/_torch/auto_deploy/_utils_test/_model_test_utils.py:269-275
Timestamp: 2025-08-27T16:59:12.325Z
Learning: In FP8 quantized linear layers, bias should be kept in high precision (typically float32) rather than being quantized to FP8 or cast to half precision, as bias is added after the matrix multiplication and high precision bias helps maintain numerical accuracy.
🧬 Code graph analysis (1)
tensorrt_llm/models/modeling_utils.py (1)
tensorrt_llm/parameter.py (1)
raw_value(198-206)
🔇 Additional comments (1)
tensorrt_llm/models/modeling_utils.py (1)
1237-1240: Fix restores fused bias in FP8 path — good catch.Concatenating gate/fc biases for the FP8-fused layer mirrors the non-FP8 path and should eliminate the previous non-determinism from uninitialized bias.
Linda-Stadter
force-pushed
the
5454559
branch
from
ee40bd8 to
8c43b32
Compare
|
/bot run |
|
PR_Github #18023 [ run ] triggered by Bot |
|
PR_Github #18023 [ run ] completed with state |
…IA#7449) Signed-off-by: Linda-Stadter <[email protected]> Signed-off-by: Gergely Magyar <[email protected]>
4 participants
Description
This change fixes a bug in the trt backend workflow that caused non-deterministic behavior for an FP8 engine that has biases enabled in the MLP layer. See bug description
Fix: Adding logic to handle the bias term when fusing gate and fc layers in combination with FP8 quantization. Without this step, the bias term will contain random values.
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
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.
Summary by CodeRabbit