[None][doc] update feature_combination_matrix doc #6691
Conversation
📝 WalkthroughWalkthroughUpdated the Torch features compatibility matrix in documentation: changed several entries for "KV Cache Reuse", "Slide Window Attention", "Logits Post Processor (Overlap Scheduler)", and one "Torch Sampler" cell to reflect new compatibility statuses. No code or public API changes. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Possibly related PRs
Suggested labels
Suggested reviewers
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
✨ 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
|
|
/bot run |
![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)
docs/source/torch/features/feature_combination_matrix.md (1)
15-15: Add a reproducible reference for the new “Yes” claimThe matrix now lists “Yes” for
KV Cache Reuse × MTP, but the reader has no citation or foot-note to understand how this was validated (e.g., thecache_hit_rate > 0check inpy_executor.py).
Consider appending a short foot-note or link to the exact test so others can reproduce the evidence behind the status.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/source/torch/features/feature_combination_matrix.md(1 hunks)
🧰 Additional context used
🧠 Learnings (2)
📓 Common learnings
Learnt from: zhengd-nv
PR: NVIDIA/TensorRT-LLM#6633
File: cpp/tensorrt_llm/batch_manager/dataTransceiverImpl.cpp:145-155
Timestamp: 2025-08-06T08:18:28.669Z
Learning: In cpp/tensorrt_llm/batch_manager/dataTransceiverImpl.cpp, the existing `mMtxForMap` mutex in DataSenderImpl is sufficient to synchronize measurement file operations in the `release` method, as all file operations occur within the same critical section that protects the `mRequestToSession` map access.
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
📚 Learning: in tensorrt-llm testing, it's common to have both cli flow tests (test_cli_flow.py) and pytorch api ...
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.
Applied to files:
docs/source/torch/features/feature_combination_matrix.md
🔇 Additional comments (1)
docs/source/torch/features/feature_combination_matrix.md (1)
16-16: Clarify the reason for the “No” status or keep it “Untested”
Slide Window Attention × MTPchanged from “Untested” to “No”, yet the PR description only states that this combination errors out due to a missingnum_nextn_predict_layersattribute.
If the incompatibility is definitive, add a brief foot-note explaining the failure; otherwise, revert to “Untested” until the root cause is resolved.
|
PR_Github #14423 [ run ] triggered by Bot |
|
PR_Github #14423 [ run ] completed with state |
leslie-fang25
changed the title
leslie-fang25
force-pushed
the
leslie/update_mtp_feature_combination
branch
from
b3b759b to
e4965c5
Compare
|
/bot run |
|
PR_Github #15288 [ run ] triggered by Bot |
|
PR_Github #15288 [ run ] completed with state |
leslie-fang25
force-pushed
the
leslie/update_mtp_feature_combination
branch
from
e5a0354 to
c04663c
Compare
|
/bot run |
|
PR_Github #15395 [ run ] triggered by Bot |
|
PR_Github #15395 [ run ] completed with state |
Signed-off-by: leslie-fang25 <leslief@nvidia.com>
leslie-fang25
force-pushed
the
leslie/update_mtp_feature_combination
branch
from
7b190ed to
bd879ce
Compare
Hi @mikeiovine, sorry for the interruption. When you have a moment, could you please review this PR especially for the change of |
|
/bot run |
|
PR_Github #15908 [ run ] triggered by Bot |
|
PR_Github #15908 [ run ] completed with state |
4 participants
Summary by CodeRabbit
Description
This PR mainly update the feature combination matrix:
MTPwithKV Cache ReuseasYescache_hit_rateTensorRT-LLM/tensorrt_llm/_torch/pyexecutor/py_executor.py
Line 573 in 413a83f
MTPtest case.MTPwithSWAasNomtp_config = MTPDecodingConfig(num_nextn_predict_layers=2)to casetest_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtypegot the error msg asAttributeError: 'Gemma3TextConfig' object has no attribute 'num_nextn_predict_layers'Overlap SchedulerwithLogits Post ProcessorasYespython -u -m pytest -s -v tests/unittest/llmapi/test_llm_pytorch.py -k test_tinyllama_logits_processor[False]SWAwithchunked prefillasYespython -u -m pytest -s -v tests/integration/defs/accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_chunked_prefillEagle3 two modelwithKV Cache reuseasYescache_hit_rateTensorRT-LLM/tensorrt_llm/_torch/pyexecutor/py_executor.py
Line 573 in 413a83f
tests/integration/defs/accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_eagle3Test 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.