[https://nvbugs/5740075][fix] Fix sm120 speculation #10049
Conversation
mikeiovine
force-pushed
the
fix-sm120-xqa
branch
from
86828f7 to
5efd3af
Compare
📝 WalkthroughWalkthroughThis PR modifies the speculative decoding extension logic to condition behavior on GPU SM versions 90/100 support, and re-enables previously skipped integration tests for guided decoding and model-specific variants. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes
Pre-merge checks and finishing touches✅ Passed checks (3 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 |
mikeiovine
force-pushed
the
fix-sm120-xqa
branch
from
5efd3af to
605ee53
Compare
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
![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/speculative/interface.py (1)
129-141: Enhance docstring to document SM version dependency.The docstring should mention that the behavior depends on SM architecture and XQA kernel availability. This will improve code maintainability and help future developers understand why certain SM versions are handled differently.
Apply this diff to improve the docstring:
def extend_ctx(self, attention_backend: Type[AttentionBackend]): """ If true, treat generation requests with draft tokens as chunked context requests at the kernel level. + + Note: For TrtllmAttention backend, this returns False only on + SM architectures that support XQA kernels (currently SM90, SM100). + Other SM versions fall back to extended context mode. """
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tensorrt_llm/_torch/speculative/interface.py(1 hunks)tests/integration/test_lists/waives.txt(0 hunks)
💤 Files with no reviewable changes (1)
- tests/integration/test_lists/waives.txt
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: The 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 in Python, even if only one class or function from a module is used (e.g., usefrom package.subpackage import fooand thenfoo.SomeClass()instead offrom package.subpackage.foo import SomeClass)
Python filenames should use snake_case (e.g.,some_file.py)
Python class names should use PascalCase (e.g.,class SomeClass)
Python function and method names should use snake_case (e.g.,def my_awesome_function():)
Python local variable names should use snake_case, with prefixkfor variable names that start with a number (e.g.,k_99th_percentile = ...)
Python global variables should use upper snake_case with prefixG(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
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 type and description (e.g.,self.x = 5followed by"""<type>: Description of 'x'""")
Avoid using reflection in Python when functionality can be easily achieved without reflection
When using try-except blocks in Python, limit the except clause to the smallest set of specific errors possible instead of catching all exceptions
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 and use the else block to implement the logic
Files:
tensorrt_llm/_torch/speculative/interface.py
**/*.{cpp,h,cu,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code files should contain an NVIDIA copyright header that includes the current year at the top
Files:
tensorrt_llm/_torch/speculative/interface.py
🧬 Code graph analysis (1)
tensorrt_llm/_torch/speculative/interface.py (1)
tensorrt_llm/_torch/attention_backend/trtllm.py (1)
TrtllmAttention(1381-1929)
⏰ 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/speculative/interface.py (2)
11-11: LGTM: Import addition is correct.The import of
get_sm_versionis necessary for the SM version check introduced in theextend_ctxmethod.
139-141: The hardcoded SM version list is correct; no changes needed.The
xqa_supportedcheck for SM versions (90, 100) is intentional. SM 100 represents Blackwell B200, which supports XQA kernels, while SM 103 (Blackwell Ultra/B300) and SM 120+ do not. The logic correctly implements the PR objective by treating SM120 as lacking XQA support, causingextend_ctxto returnTruefor TrtllmAttention on that architecture. The list is not incomplete—it reflects which architectures actually have XQA kernel support.
|
PR_Github #28596 [ run ] triggered by Bot. Commit: |
|
PR_Github #28596 [ run ] completed with state
|
|
/bot run --stage-list "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1" --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1" |
|
PR_Github #28653 [ run ] triggered by Bot. Commit: |
|
PR_Github #28653 [ run ] completed with state |
|
/bot run --stage-list "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1,RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1,RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
1 similar comment
|
/bot run --stage-list "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1,RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1,RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
mikeiovine
force-pushed
the
fix-sm120-xqa
branch
from
605ee53 to
f3554af
Compare
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
1 similar comment
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
|
PR_Github #28824 [ run ] triggered by Bot. Commit: |
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
|
PR_Github #28948 [ run ] triggered by Bot. Commit: |
|
PR_Github #28948 [ run ] completed with state
|
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
|
PR_Github #29402 [ run ] triggered by Bot. Commit: |
|
PR_Github #29402 [ run ] completed with state
|
mikeiovine
force-pushed
the
fix-sm120-xqa
branch
from
c629637 to
62cc483
Compare
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
|
PR_Github #30194 [ run ] triggered by Bot. Commit: |
|
PR_Github #30194 [ run ] completed with state
|
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
|
PR_Github #30222 [ run ] triggered by Bot. Commit: |
|
PR_Github #30222 [ run ] completed with state
|
mikeiovine
force-pushed
the
fix-sm120-xqa
branch
from
62cc483 to
721eab1
Compare
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
|
PR_Github #30395 [ run ] triggered by Bot. Commit: |
|
PR_Github #30395 [ run ] completed with state
|
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
mikeiovine
force-pushed
the
fix-sm120-xqa
branch
from
721eab1 to
6ae0908
Compare
|
/bot run --extra-stage "RTXPro6000D-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000D-4_GPUs-PyTorch-Post-Merge-2" |
|
PR_Github #31099 [ run ] triggered by Bot. Commit: |
mikeiovine
force-pushed
the
fix-sm120-xqa
branch
from
6ae0908 to
b6a8f58
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #31110 [ run ] triggered by Bot. Commit: |
Signed-off-by: Mike Iovine <[email protected]>
mikeiovine
force-pushed
the
fix-sm120-xqa
branch
from
b6a8f58 to
37215e6
Compare
|
/bot run --disable-fail-fast |
|
Note: keeping The other unwaived test was run locally, no need for post-merge CI |
|
PR_Github #31116 [ run ] triggered by Bot. Commit: |
|
PR_Github #31116 [ run ] completed with state |
6 participants
Description
The XQA kernels are not available on sm120. Switch back to
extend_ctx = Truefor this case.Test Coverage
Existing tests.
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.
Summary by CodeRabbit
Bug Fixes
Tests
✏️ Tip: You can customize this high-level summary in your review settings.