[None][fix] add quantization check for DeepEP LL low precision combine in new moe comm api #10072
Conversation
|
/bot run |
📝 WalkthroughWalkthroughThe PR adds a new method Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tensorrt_llm/_torch/modules/fused_moe/communication/deep_ep_low_latency.py (1)
101-101: Logic is correct; consider extracting common quant mode check.The quant mode check is identical to line 107 in
supports_low_precision_combine(). While the methods serve different purposes (post-quant dispatch vs. low-precision combine), extracting the common condition into a private helper like_has_supported_quant_mode()would reduce duplication.Example refactor:
def _has_supported_quant_mode(self) -> bool: """Check if any supported quantization mode is enabled (nvfp4, fp8_qdq, w4afp8)""" return self._has_nvfp4() or self._has_fp8_qdq() or self._has_w4afp8() def supports_post_quant_dispatch(self) -> bool: """DeepEP Low Latency supports post-quant for: fp8_qdq, nvfp4, w4afp8""" if not self.enable_postquant_alltoall: return False return self._has_supported_quant_mode() def supports_low_precision_combine(self) -> bool: """DeepEP Low Latency supports low-precision combine for: fp8_qdq, nvfp4, w4afp8""" return self._has_supported_quant_mode()
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tensorrt_llm/_torch/modules/fused_moe/communication/deep_ep_low_latency.py(2 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Code developed for TensorRT-LLM should conform to Python 3.8+
Indent Python code with 4 spaces. Do not use tabs
Always maintain the namespace when importing, even if only one class or function from a module is used (e.g., usefrom package.subpackage import foo; foo.SomeClass()instead offrom package.subpackage.foo import SomeClass)
Python filenames should use snake_case (e.g.,some_file.py)
Python classes should use PascalCase (e.g.,class SomeClass)
Python functions and methods should use snake_case (e.g.,def my_awesome_function():)
Python local variables should use snake_case. Prefix 'k' for variable names that start with a number (e.g.,k_99th_percentile = ...)
Python global variables should use upper snake_case and prefix 'G' (e.g.,G_MY_GLOBAL = ...)
Python constants should use upper snake_case (e.g.,MY_CONSTANT = ...)
Avoid shadowing variables declared in an outer scope in Python code
Initialize all externally visible members of a Python class in the constructor
For Python interfaces that may be used outside a file, prefer docstrings over comments
Python comments should be reserved for code within a function, or interfaces that are local to a file
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx
Python attributes and variables can be documented inline with attribute docstrings that will be rendered under the class docstring
Avoid using reflection in Python when functionality can be easily achieved without reflection
When using try-except blocks in Python, limit the except to the smallest set of errors possible
When using try-except blocks in Python to handle multiple possible variable types (duck-typing), keep the body of the try as small as possible, using the else block to implement the logic
Files:
tensorrt_llm/_torch/modules/fused_moe/communication/deep_ep_low_latency.py
**/*.{h,hpp,cpp,cc,cxx,cu,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM source code files should contain an NVIDIA copyright header with the current year, including .cpp, .h, .cu, .py, and other source files
Files:
tensorrt_llm/_torch/modules/fused_moe/communication/deep_ep_low_latency.py
🧠 Learnings (2)
📓 Common learnings
Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 6915
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu:4010-4012
Timestamp: 2025-08-14T23:23:27.449Z
Learning: For MOE (Mixture of Experts) code reviews in TensorRT-LLM, avoid repeatedly suggesting finalize fusion validation checks and safety assertions. The user djns99 has indicated these suggestions are repetitive and unwanted across multiple MOE-related changes.
Learnt from: venkywonka
Repo: NVIDIA/TensorRT-LLM PR: 6029
File: .github/pull_request_template.md:45-53
Timestamp: 2025-08-27T17:50:13.264Z
Learning: For PR templates in TensorRT-LLM, avoid suggesting changes that would increase developer overhead, such as converting plain bullets to mandatory checkboxes. The team prefers guidance-style bullets that don't require explicit interaction to reduce friction in the PR creation process.
📚 Learning: 2025-08-21T02:39:12.009Z
Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 7104
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu:1475-1480
Timestamp: 2025-08-21T02:39:12.009Z
Learning: The min latency mode functionality in TensorRT-LLM MOE kernels (cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu) is deprecated and no longer being maintained/updated, as confirmed by djns99. Bug reports and optimization suggestions for the computeStridesTmaWarpSpecializedLowLatencyKernel and related min latency code paths should be deprioritized.
Applied to files:
tensorrt_llm/_torch/modules/fused_moe/communication/deep_ep_low_latency.py
⏰ 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 (2)
tensorrt_llm/_torch/modules/fused_moe/communication/deep_ep_low_latency.py (2)
62-64: LGTM! Proper guard for low precision combine.The guard correctly ensures
use_low_precision_combineis only enabled when both the user requests it and the platform supports it viasupports_low_precision_combine().
103-107: LGTM! New method correctly indicates low-precision combine support.The method properly checks for supported quantization modes and is used appropriately in the initialization guard at line 63.
|
PR_Github #28705 [ run ] triggered by Bot. Commit: |
|
/bot run |
|
PR_Github #28730 [ run ] triggered by Bot. Commit: |
|
PR_Github #28730 [ run ] completed with state
|
|
/bot run |
|
PR_Github #28882 [ run ] triggered by Bot. Commit: |
|
PR_Github #28882 [ run ] completed with state
|
|
/bot run |
|
PR_Github #28935 [ run ] triggered by Bot. Commit: |
|
PR_Github #28935 [ run ] completed with state
|
yilin-void
force-pushed
the
fix/lp_combine
branch
from
ac713ad to
6707251
Compare
|
/bot run |
|
PR_Github #29073 [ run ] triggered by Bot. Commit: |
|
PR_Github #29073 [ run ] completed with state
|
yilin-void
force-pushed
the
fix/lp_combine
branch
from
6707251 to
01327ed
Compare
|
/bot run |
|
PR_Github #29410 [ run ] triggered by Bot. Commit: |
|
PR_Github #29410 [ run ] completed with state
|
|
/bot run |
|
PR_Github #29563 [ run ] triggered by Bot. Commit: |
|
PR_Github #29563 [ run ] completed with state
|
|
PR_Github #30699 [ run ] triggered by Bot. Commit: |
|
PR_Github #30699 [ run ] completed with state
|
|
/bot run |
|
PR_Github #30826 [ run ] triggered by Bot. Commit: |
|
PR_Github #30826 [ run ] completed with state
|
|
/bot run |
|
PR_Github #30982 [ run ] triggered by Bot. Commit: |
|
/bot run |
|
PR_Github #30987 [ run ] triggered by Bot. Commit: |
|
PR_Github #30982 [ run ] completed with state |
|
PR_Github #30987 [ run ] completed with state
|
|
/bot run |
|
PR_Github #31207 [ run ] triggered by Bot. Commit: |
|
PR_Github #31207 [ run ] completed with state
|
comm api Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
yilin-void
force-pushed
the
fix/lp_combine
branch
from
f72b25a to
4356aea
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #31469 [ run ] triggered by Bot. Commit: |
|
PR_Github #31469 [ run ] completed with state
|
|
/bot run --disable-fail-fast |
|
PR_Github #31728 [ run ] triggered by Bot. Commit: |
|
PR_Github #31728 [ run ] completed with state
|
|
/bot run --disable-fail-fast |
|
PR_Github #31874 [ run ] triggered by Bot. Commit: |
|
PR_Github #31874 [ run ] completed with state
|
|
/bot run --disable-fail-fast |
|
PR_Github #32034 [ run ] triggered by Bot. Commit: |
|
PR_Github #32034 [ run ] completed with state |
…e in new moe comm api (NVIDIA#10072) Signed-off-by: Yilin Zhang <18275976+yilin-void@users.noreply.github.com>
3 participants
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.
Description
Test Coverage
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
Update tava architecture diagram if there is a significant design change in PR.
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.
Details
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.