[#8813][fix] Add missing event for block onboard for the kv cache tra… #8874
Conversation
|
/bot run --disable-fail-fast |
📝 WalkthroughWalkthroughIntroduces CUDA event-based synchronization for KV cache block onboarding. Blocks store pending onboard events set during transfer, which are waited on before use to ensure full onboarding completion. Changes
Sequence DiagramsequenceDiagram
participant TransferMgr as Transfer Manager
participant Block as KV Cache Block
participant BlockMgr as Block Manager
TransferMgr->>TransferMgr: Copy block to GPU
TransferMgr->>TransferMgr: Create CUDA event
TransferMgr->>TransferMgr: Record event on onboard stream
TransferMgr->>Block: setPendingOnboardEvent(event)
rect rgb(200, 220, 240)
Note over BlockMgr: Later, when adding block to beam
BlockMgr->>Block: getPendingOnboardEvent()
alt Event present
BlockMgr->>BlockMgr: Wait on event via buffer stream
BlockMgr->>Block: clearPendingOnboardEvent()
end
end
BlockMgr->>BlockMgr: Use block (fully onboarded)
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ 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: 1
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
cpp/include/tensorrt_llm/batch_manager/kvCacheManager.h(2 hunks)cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp(1 hunks)cpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp(1 hunks)
🧰 Additional context used
📓 Path-based instructions (7)
**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh}: Namespace closing braces must include a trailing comment with the namespace name (e.g., '} // namespace foo').
Prefer const or constexpr variables over #define for constants.
Declare variables that are not modified after initialization as const.
Avoid magic literals in code; except for 0, nullptr, true, false. Use named constants for comparisons and logic.
Use Allman brace style for formatting.
Place the semicolon of an empty for/while loop on a new line.
Bodies of switch/while/do-while/for must be compound statements (brace-delimited), and if/else must always be followed by brace-delimited statements.
Type names (e.g., classes) must be CamelCase starting with an uppercase letter (e.g., FooBar).
Local variables, methods, and namespaces use lowerCamelCase (e.g., localFooBar).
Non-magic-number global variables that are non-static and not in an anonymous namespace must be lowerCamelCase prefixed with 'g' (e.g., gDontUseGlobalFoos).
Non-magic-number globals that are static or in an anonymous namespace use lowerCamelCase prefixed with 's' (e.g., sMutableStaticGlobal).
Locally visible static variables use lowerCamelCase with 's' prefix (e.g., static std::once_flag sFlag).
Private/protected member variables use 'm' prefix with CamelCase (e.g., mNbFooValues). Public members may omit, but 'm' is encouraged for clarity.
Constants (enums, global constants, static constants, and function-scope magic/literal constants) use uppercase SNAKE_CASE with 'k' prefix (e.g., kDIGIT_NUM).
Function-scope constants that are not magic numbers or literals are named like non-constant variables (e.g., bool const pass = a && b).
If macros are necessary, name them in UPPER_SNAKE_CASE (e.g., FOO_VERSION) and prefer constants over #define.
Use LLVM clang-format; wrap lines at a maximum of 120 columns; use '// clang-format off/on' sparingly with justification.
Use smart pointers for heap allocations; prefer unique_ptr for sole ownership, shared_ptr for shared...
Files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
**/*.{cpp,cxx,cc,cu,h,hpp,hh,hxx,cuh}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
C++ filenames should be lowerCamelCase (first letter lowercase) and must be case-insensitive unique within a compilation target.
Files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
**/*.{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:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
**/*.{h,hpp,hh,hxx,cpp,cxx,cc}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.{h,hpp,hh,hxx,cpp,cxx,cc}: Prefer anonymous namespaces over 'static' for internal linkage of functions.
All templates (class/function/member/static) must be instantiated at least once; non-POD classes should have private data members.
Files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
**/*.{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:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
**/*.{h,hpp,hh,hxx}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Document new class interfaces and function prototypes with Doxygen; use //! for single-line and //!< for members.
Files:
cpp/include/tensorrt_llm/batch_manager/kvCacheManager.h
**/*.{h,hpp,hh,hxx,cuh}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use include guards named 'TRTLLM_<FILE_NAME_IN_CAPS_WITH_UNDERSCORES>_H' (no leading or trailing underscore; directory names excluded).
Files:
cpp/include/tensorrt_llm/batch_manager/kvCacheManager.h
🧠 Learnings (10)
📓 Common learnings
Learnt from: thorjohnsen
Repo: NVIDIA/TensorRT-LLM PR: 6910
File: cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp:0-0
Timestamp: 2025-08-14T21:04:50.248Z
Learning: In KV cache onboarding logic during prefill in cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp, when calculating which blocks fall within the attention window, use getTokensPerBlock() to advance token indices rather than block->getUniqueTokens().size(), because the calculation needs to consider the post-prefill state where blocks will be filled to capacity, not their current token count.
📚 Learning: 2025-08-14T21:04:50.248Z
Learnt from: thorjohnsen
Repo: NVIDIA/TensorRT-LLM PR: 6910
File: cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp:0-0
Timestamp: 2025-08-14T21:04:50.248Z
Learning: In KV cache onboarding logic during prefill in cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp, when calculating which blocks fall within the attention window, use getTokensPerBlock() to advance token indices rather than block->getUniqueTokens().size(), because the calculation needs to consider the post-prefill state where blocks will be filled to capacity, not their current token count.
Applied to files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
📚 Learning: 2025-08-15T06:46:54.897Z
Learnt from: eopXD
Repo: NVIDIA/TensorRT-LLM PR: 6767
File: cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp:0-0
Timestamp: 2025-08-15T06:46:54.897Z
Learning: In cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp addToken function, newly allocated blocks are unshared by design. The beam search path in addToken (when sequence.getNumTokens() > windowSize) is currently broken/non-functional with SWA, so the block allocation doesn't follow a shared-then-unshared pattern.
Applied to files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
📚 Learning: 2025-08-20T06:56:02.889Z
Learnt from: eopXD
Repo: NVIDIA/TensorRT-LLM PR: 6768
File: cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp:577-579
Timestamp: 2025-08-20T06:56:02.889Z
Learning: In cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp, maxSequenceLength is now enforced as a non-optional argument in the BlockManager constructor, so concerns about std::nullopt defaulting to 0 are not applicable. When windowSize > maxSequenceLength, a warning should be added instead of handling optional parameter cases.
Applied to files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
📚 Learning: 2025-08-21T09:41:49.347Z
Learnt from: eopXD
Repo: NVIDIA/TensorRT-LLM PR: 6768
File: cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp:2010-2045
Timestamp: 2025-08-21T09:41:49.347Z
Learning: In cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp, updateSequenceCacheBlockOffsets is specifically for updating bookkeeping when blocks are added during the context phase, not for refreshing offsets after detach operations. During detach operations, GenerationRequest::removeFrontBlock handles the necessary cache block bookkeeping internally.
Applied to files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
📚 Learning: 2025-08-20T06:48:45.368Z
Learnt from: eopXD
Repo: NVIDIA/TensorRT-LLM PR: 6768
File: cpp/include/tensorrt_llm/batch_manager/kvCacheManager.h:0-0
Timestamp: 2025-08-20T06:48:45.368Z
Learning: In cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp, updateSequenceCacheBlockOffsets is only called when adding a sequence, not during detach operations. During detach, the cache block bookkeeping is handled by GenerationRequest::removeFrontBlock.
Applied to files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cppcpp/include/tensorrt_llm/batch_manager/kvCacheManager.hcpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp
📚 Learning: 2025-08-15T06:46:53.813Z
Learnt from: eopXD
Repo: NVIDIA/TensorRT-LLM PR: 6767
File: cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp:0-0
Timestamp: 2025-08-15T06:46:53.813Z
Learning: In the TensorRT-LLM KV cache manager, SWA (Sliding Window Attention) combined with beam search is currently in a broken/non-functional state and is planned for future rework. During preparatory refactoring phases, code related to SWA+beam search may intentionally remain in a non-working state until the broader rework is completed.
Applied to files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp
📚 Learning: 2025-08-06T08:18:28.669Z
Learnt from: zhengd-nv
Repo: NVIDIA/TensorRT-LLM PR: 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.
Applied to files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp
📚 Learning: 2025-08-20T06:48:45.368Z
Learnt from: eopXD
Repo: NVIDIA/TensorRT-LLM PR: 6768
File: cpp/include/tensorrt_llm/batch_manager/kvCacheManager.h:0-0
Timestamp: 2025-08-20T06:48:45.368Z
Learning: There is a planned refactoring to move cache block bookkeeping utilities from BlockManager/WindowBlockManager into the GenerationRequest class itself to improve code organization and make responsibilities clearer.
Applied to files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp
📚 Learning: 2025-08-13T16:20:37.987Z
Learnt from: dcampora
Repo: NVIDIA/TensorRT-LLM PR: 6867
File: tensorrt_llm/_torch/pyexecutor/sampler.py:67-72
Timestamp: 2025-08-13T16:20:37.987Z
Learning: In TensorRT-LLM sampler code, performance is prioritized over additional validation checks. The beam_width helper method intentionally returns the first request's beam_width without validating consistency across all requests to avoid performance overhead from iterating through the entire batch.
Applied to files:
cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp
🧬 Code graph analysis (1)
cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp (1)
cpp/tests/unit_tests/kernels/mixtureOfExpertsTest.cu (1)
mBufferManager(241-245)
⏰ 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)
cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp (1)
1486-1491: LGTM - Proper synchronization before block usage.The implementation correctly ensures that any pending onboard operation completes before the block is used by:
- Checking for a pending onboard event
- Waiting on the buffer manager's stream if an event exists
- Clearing the event after the wait
This prevents race conditions where a block could be accessed before its data has been fully transferred from secondary to primary memory.
cpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp (1)
227-229: LGTM - Correct event instrumentation for onboard completion.The implementation properly records a CUDA event after the block copy operation and stores it in the block. The event is:
- Created after
copyBlockcompletes (line 226), ensuring it tracks the copy operation- Recorded on the onboard stream (line 228), matching the stream used for the copy
- Moved into the block (line 229), transferring ownership for later synchronization
This enables downstream code to wait for onboard completion before using the block.
…he transfer manager Authored-by: @josephrocca Co-authored-by: eopXD <[email protected]> Signed-off-by: eopXD <[email protected]>
|
PR_Github #23355 [ run ] triggered by Bot. Commit: |
eopXD
force-pushed
the
fix-kv-cache-onboard-transfer
branch
from
1087f65 to
524ad7b
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #23359 [ run ] triggered by Bot. Commit: |
|
PR_Github #23355 [ run ] completed with state |
|
Dropping this pull request since we have a better approach in #8890 |
2 participants
Summary by CodeRabbit
Release Notes
Description
The onboad event is missing, which will cause block corruption in many circumstances.
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
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.