[None][feat] Make 2-model spec dec use the 1-model kernels (Hopper) #8810
Conversation
|
/bot run --disable-fail-fast |
📝 WalkthroughWalkthroughSimplify speculative decoding logic by removing conditional branching in context extension and attention mode determination, and update method signatures with new parameters. Rename test function and adjust acceptance rate threshold. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 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: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
tensorrt_llm/_torch/speculative/interface.py (1)
121-134: Remove unused parameters or implement their logic inattention_need_spec_dec_mode.The method signature adds five new required parameters, but only three (
spec_resource_manager,is_draft_model,attention_backend) are actually used in the implementation. The parametersuse_chain_drafterandis_spec_dec_treeare declared but never referenced in the method body (lines 129-134), creating dead code.• At interface.py lines 121-134: Either remove the unused parameters from the signature, or implement the logic that should use them.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
tensorrt_llm/_torch/speculative/interface.py(2 hunks)tests/unittest/_torch/speculative/test_eagle3.py(2 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/_torch/speculative/interface.pytests/unittest/_torch/speculative/test_eagle3.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/_torch/speculative/interface.pytests/unittest/_torch/speculative/test_eagle3.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/_torch/speculative/interface.pytests/unittest/_torch/speculative/test_eagle3.py
🧠 Learnings (1)
📚 Learning: 2025-08-14T15:38:01.771Z
Learnt from: MatthiasKohl
PR: NVIDIA/TensorRT-LLM#6904
File: cpp/tensorrt_llm/pybind/thop/bindings.cpp:55-57
Timestamp: 2025-08-14T15:38:01.771Z
Learning: In TensorRT-LLM Python bindings, tensor parameter collections like mla_tensor_params and spec_decoding_tensor_params are kept as required parameters without defaults to maintain API consistency, even when it might affect backward compatibility.
Applied to 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(1156-1595)
🪛 Ruff (0.14.2)
tests/unittest/_torch/speculative/test_eagle3.py
58-58: Unused function argument: request
(ARG001)
⏰ 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)
tests/unittest/_torch/speculative/test_eagle3.py (1)
139-139: Verify the acceptance rate threshold adjustment is appropriate.The acceptance rate threshold has been lowered from 0.15 to 0.10. While the PR objectives indicate this change is due to floating-point differences when switching to 1-model kernels, ensure this relaxed threshold still provides meaningful validation and doesn't mask potential performance regressions.
tensorrt_llm/_torch/speculative/interface.py (1)
109-119: Simplifiedextend_ctximplementation is correct and complete.The simplified logic properly handles all cases:
- Returns
Falsefor 1-engine deployments (which have separate draft token handling)- Returns
FalseforTrtllmAttentionbackend (which doesn't support chunked context extension)- Returns
Truefor all other backends (VanillaAttention,FlashInferAttention,StarAttention), enabling chunked context handlingAll three callers in
model_engine.py(lines 1355, 1409, 1673) use this return value consistently for branching logic, and no regressions are introduced by the simplification.
|
PR_Github #23084 [ run ] triggered by Bot. Commit: |
|
PR_Github #23084 [ run ] completed with state |
mikeiovine
force-pushed
the
2-model-kernels
branch
from
2e00216 to
b146eef
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #23219 [ run ] triggered by Bot. Commit: |
|
PR_Github #23219 [ run ] completed with state |
mikeiovine
force-pushed
the
2-model-kernels
branch
from
b146eef to
ce7462c
Compare
|
/bot run |
|
PR_Github #23435 [ run ] triggered by Bot. Commit: |
|
PR_Github #23435 [ run ] completed with state |
|
/bot run |
|
PR_Github #23682 [ run ] triggered by Bot. Commit: |
|
PR_Github #23682 [ run ] completed with state |
Signed-off-by: Mike Iovine <[email protected]>
mikeiovine
force-pushed
the
2-model-kernels
branch
from
073aef2 to
c3f89c4
Compare
|
Putting this PR on hold until #8706 is merged. Tests with the overlap scheduler on will be buggy without the fixes in 8706 otherwise |
3 participants
Description
Make 2-model use the same XQA kernels as 1-model. Should improve perf.
Test Coverage
Existing tests. Had to relax them a bit as AR changes. I think it's just floating point error though, the new ARs match 1-model.
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
Refactor
Tests