[https://nvbugs/5575920][fix] Fix cublas/cublasLt handle creation memory not sufficient error #8900
Conversation
Signed-off-by: Wangshanshan <[email protected]>
…uce max tokens in kv cache config. Signed-off-by: Wangshanshan <[email protected]>
…uce memory fraction in kv cache config. Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Wangshanshan <[email protected]>
Signed-off-by: Wangshanshan <[email protected]>
📝 WalkthroughWalkthroughEnhances CUDA handle management with GPU memory monitoring and improves error reporting during cublasHandle and cublasLtHandle creation/destruction. Updates integration tests to explicitly configure GPU memory fractions for fp8 scenarios to prevent allocation errors. Changes
Sequence DiagramsequenceDiagram
participant Client
participant opUtils as opUtils.cpp
participant CUDA as CUDA/cuBLAS
rect rgb(240, 250, 255)
Note over opUtils,CUDA: Handle Creation Flow (with monitoring)
Client->>opUtils: Create cublasHandle_t
opUtils->>opUtils: Get current CUDA context
opUtils->>opUtils: Log current memory usage
opUtils->>CUDA: cublasCreate()
alt Success
CUDA-->>opUtils: CUBLAS_STATUS_SUCCESS
opUtils-->>Client: Handle created
else Failure
CUDA-->>opUtils: Error status
opUtils->>opUtils: Fetch memory info
opUtils->>opUtils: Construct error with memory context
opUtils-->>Client: throw CublasException with memory info
end
end
rect rgb(255, 245, 240)
Note over opUtils,CUDA: Handle Destruction Flow (with logging)
Client->>opUtils: Destroy cublasHandle_t
opUtils->>CUDA: cublasDestroy()
alt Success
CUDA-->>opUtils: CUBLAS_STATUS_SUCCESS
opUtils-->>Client: Handle destroyed
else Failure
CUDA-->>opUtils: Error status
opUtils->>opUtils: Log warning with error status
opUtils-->>Client: Continue (non-throwing)
end
end
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 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: 0
🧹 Nitpick comments (1)
cpp/tensorrt_llm/common/opUtils.cpp (1)
328-356: LGTM: Consistent pattern for cublasLt handle management.The
getCublasLtHandle()implementation mirrors the improvements ingetCublasHandle(), ensuring consistent error reporting and diagnostics across both cuBLAS handle types.Optional: Consider reducing code duplication.
The nearly identical pattern between
getCublasHandle()andgetCublasLtHandle()could be refactored into a generic helper template:template <typename HandleT, typename CreateFn, typename DestroyFn> std::shared_ptr<HandleT> createCublasHandleWithLogging( const char* handleName, CreateFn createFn, DestroyFn destroyFn) { // Common logic for context retrieval, logging, creation, and error handling }This would centralize the memory monitoring and error handling logic, but the current approach is perfectly acceptable given the small number of handle types.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
cpp/tensorrt_llm/common/opUtils.cpp(2 hunks)tests/integration/defs/accuracy/test_llm_api_pytorch.py(2 hunks)
🧰 Additional context used
📓 Path-based instructions (6)
**/*.{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/common/opUtils.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/common/opUtils.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/common/opUtils.cpptests/integration/defs/accuracy/test_llm_api_pytorch.py
**/*.{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/common/opUtils.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/common/opUtils.cpptests/integration/defs/accuracy/test_llm_api_pytorch.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:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧠 Learnings (9)
📓 Common learnings
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.
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/kernels/nccl_device/multimem.h:20-30
Timestamp: 2025-09-23T15:13:48.819Z
Learning: TRT-LLM targets modern CUDA toolkits that support FP8 datatypes, so cuda_fp8.h can be included unconditionally without version guards in TRT-LLM code.
📚 Learning: 2025-09-23T15:13:48.819Z
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/kernels/nccl_device/multimem.h:20-30
Timestamp: 2025-09-23T15:13:48.819Z
Learning: TRT-LLM targets modern CUDA toolkits that support FP8 datatypes, so cuda_fp8.h can be included unconditionally without version guards in TRT-LLM code.
Applied to files:
cpp/tensorrt_llm/common/opUtils.cpp
📚 Learning: 2025-09-23T15:01:00.070Z
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/kernels/nccl_device/config.cu:15-17
Timestamp: 2025-09-23T15:01:00.070Z
Learning: In TensorRT-LLM NCCL device kernels (cpp/tensorrt_llm/kernels/nccl_device/config.cu), std::ostringstream is used but <sstream> doesn't need to be explicitly included because it's provided transitively through other headers like tensorrt_llm/common/cudaUtils.h or config.h. Local compilation testing confirms this works without the explicit include.
Applied to files:
cpp/tensorrt_llm/common/opUtils.cpp
📚 Learning: 2025-09-23T15:01:00.070Z
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/kernels/nccl_device/config.cu:15-17
Timestamp: 2025-09-23T15:01:00.070Z
Learning: In TensorRT-LLM NCCL device kernels, the <sstream> header is not needed as an explicit include in config.cu because it's provided transitively through other headers. Local compilation testing confirms this works without the explicit include.
Applied to files:
cpp/tensorrt_llm/common/opUtils.cpp
📚 Learning: 2025-08-25T00:03:39.294Z
Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 7104
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu:1185-1189
Timestamp: 2025-08-25T00:03:39.294Z
Learning: TLLM_CHECK_WITH_INFO is a host-side utility function and cannot be called from CUDA device functions (those marked with __device__ or __global__). In device code, assert() is the primary mechanism for handling "should never happen" conditions, and like standard C++ assert, CUDA's assert only works in debug builds and is compiled out in release builds.
Applied to files:
cpp/tensorrt_llm/common/opUtils.cpp
📚 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:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
📚 Learning: 2025-08-26T09:37:10.463Z
Learnt from: jiaganc
Repo: NVIDIA/TensorRT-LLM PR: 7031
File: tensorrt_llm/bench/dataclasses/configuration.py:90-104
Timestamp: 2025-08-26T09:37:10.463Z
Learning: In TensorRT-LLM's bench configuration, the `get_pytorch_perf_config()` method returns `self.pytorch_config` which is a Dict[str, Any] that can contain default values including `cuda_graph_config`, making the fallback `llm_args["cuda_graph_config"]` safe to use.
Applied to files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
📚 Learning: 2025-08-26T09:37:10.463Z
Learnt from: jiaganc
Repo: NVIDIA/TensorRT-LLM PR: 7031
File: tensorrt_llm/bench/dataclasses/configuration.py:90-104
Timestamp: 2025-08-26T09:37:10.463Z
Learning: In TensorRT-LLM, the `get_pytorch_perf_config()` method returns `self.pytorch_config` which can contain default `cuda_graph_config` values, so `llm_args` may already have this config before the extra options processing.
Applied to files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
📚 Learning: 2025-09-29T15:14:28.503Z
Learnt from: amitz-nv
Repo: NVIDIA/TensorRT-LLM PR: 8063
File: tensorrt_llm/lora_manager.py:1080-1112
Timestamp: 2025-09-29T15:14:28.503Z
Learning: In tensorrt_llm/lora_manager.py, when calculating part_sizes for attn_qkv fused LoRA modules, the sizes are correctly multiplied by tp_size because model_config.num_heads and model_config.num_kv_heads are already divided by tp_size (per-TP-rank values), so multiplication is needed to get the original full concatenated dimension size. The interleave_fused_lora_weights_for_tp function provides proper validation.
Applied to files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧬 Code graph analysis (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
tensorrt_llm/llmapi/llm_args.py (1)
KvCacheConfig(976-1110)
⏰ 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 (5)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
158-162: LGTM: Appropriate memory reservation for FP8 KV cache.The explicit
free_gpu_memory_fraction=0.8parameter ensures sufficient GPU memory remains available for cuBLAS/cuBLASLt handle creation when using FP8 KV cache. This aligns with the enhanced error reporting in the C++ changes and provides a practical workaround for memory-constrained scenarios.
196-200: LGTM: Consistent memory configuration across multi-GPU test.The same
free_gpu_memory_fraction=0.8configuration is correctly applied here, ensuring consistent memory management behavior between single-GPU and multi-GPU FP8 test scenarios.cpp/tensorrt_llm/common/opUtils.cpp (3)
255-274: LGTM: Well-designed memory monitoring utilities.The
MemoryInfostructure andgetMemoryInfo()function provide clear, efficient memory diagnostics. The conversion to MB and percentage calculation improves readability, and the defensive check fortotal_mem > 0prevents division by zero.
277-293: LGTM: Excellent error context and actionable guidance.Both
logMemoryUsage()andthrowCublasErrorWithMemInfo()provide valuable diagnostic information. The error message's suggestion to "reducekv_cache_config.free_gpu_memory_fraction" directly aligns with the test configuration changes and gives users a clear remediation path.
297-326: LGTM: Robust handle creation with improved diagnostics.The enhanced
getCublasHandle()implementation adds:
- Proactive memory logging before handle creation
- Clear error messages with memory context when creation fails
- Warning logs instead of silent failures during destruction
- Use of
make_uniquefor proper resource managementThe overhead of
cudaMemGetInfo()is negligible since handle creation is rare (once per CUDA context per thread).
Signed-off-by: Wangshanshan <[email protected]>
|
/bot run |
|
PR_Github #23568 [ run ] triggered by Bot. Commit: |
|
PR_Github #23568 [ run ] completed with state |
4 participants
Summary by CodeRabbit
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
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.