[None][feat] GPT_OSS torch compile support #10501
Conversation
|
/bot run |
|
PR_Github #30893 [ run ] triggered by Bot. Commit: |
📝 WalkthroughWalkthroughThis PR introduces a new PyTorch fake operator Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Suggested reviewers
🚥 Pre-merge checks | ✅ 1 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
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
🤖 Fix all issues with AI agents
In @tensorrt_llm/_torch/custom_ops/cpp_custom_ops.py:
- Around line 846-865: The swizzled-layout branch in the torch.library
registration for "trtllm::mxfp8_quantize" computes sf_size using only
output_shape[0], which is wrong for ND inputs; modify the isSfSwizzledLayout
branch to compute m by multiplying all leading dimensions (for i in
range(len(output_shape)-1) m *= output_shape[i]) and then set sf_size =
fp4_utils.pad_up(m, 128) * fp4_utils.pad_up(padded_k // sf_vec_size, 4) so it
matches the non-swizzled logic and the C++ implementation (refer to symbols
isSfSwizzledLayout, output_shape, m, padded_k, sf_vec_size, fp4_utils.pad_up,
and sf_size).
🧹 Nitpick comments (1)
tests/integration/defs/.test_durations (1)
276-287: LGTM! Consistent addition of eager mode variants.The addition of
-eagersuffix to all 4GPU test variants is consistent and aligns with the PR objective of adding torch compile support for GPT_OSS. The preserved durations (~745 seconds) serve as reasonable initial estimates for test scheduling.Note that these duration values should be updated after the eager variants complete their first actual runs to reflect any performance differences.
Optional: Consider rounding precision
For readability and practical purposes, the high decimal precision in some durations (e.g.,
745.0004936959594488144) could be rounded to 2-3 decimal places without affecting test scheduling accuracy:- "accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-trtllm-auto-eager]": 745.0004936959594488144, + "accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-trtllm-auto-eager]": 745.00,This is purely cosmetic and does not impact functionality.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (13)
tensorrt_llm/_torch/custom_ops/cpp_custom_ops.pytensorrt_llm/_torch/models/modeling_gpt_oss.pytests/integration/defs/.test_durationstests/integration/defs/accuracy/test_llm_api_pytorch.pytests/integration/test_lists/qa/llm_function_core.txttests/integration/test_lists/qa/llm_function_core_sanity.txttests/integration/test_lists/qa/llm_function_nim.txttests/integration/test_lists/qa/llm_function_rtx6k.txttests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/test-db/l0_dgx_b300.ymltests/integration/test_lists/test-db/l0_dgx_h100.ymltests/integration/test_lists/test-db/l0_gb200_multi_gpus.ymltests/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 Python modules, even if only one class or function from a module is used
Python filenames should use snake_case (e.g.,some_file.py)
Python classes should use PascalCase (e.g.,class SomeClass)
Python functions and methods should use snake_case (e.g.,def my_awesome_function():)
Python local variables 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
Use comments in Python 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 the format"""<type>: Description"""
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 errors possible
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 for the main logic
Files:
tensorrt_llm/_torch/models/modeling_gpt_oss.pytensorrt_llm/_torch/custom_ops/cpp_custom_ops.pytests/integration/defs/accuracy/test_llm_api_pytorch.py
**/*.{cpp,cc,cxx,h,hpp,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM source files (.cpp, .h, .cu, .py, and other source files) should contain an NVIDIA copyright header with the year of latest meaningful modification
Files:
tensorrt_llm/_torch/models/modeling_gpt_oss.pytensorrt_llm/_torch/custom_ops/cpp_custom_ops.pytests/integration/defs/accuracy/test_llm_api_pytorch.py
🧠 Learnings (18)
📓 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.
📚 Learning: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
Repo: NVIDIA/TensorRT-LLM PR: 7645
File: tests/integration/test_lists/qa/llm_function_core.txt:648-648
Timestamp: 2025-09-09T09:40:45.658Z
Learning: In TensorRT-LLM test lists, it's common and intentional for the same test to appear in multiple test list files when they serve different purposes (e.g., llm_function_core.txt for comprehensive core functionality testing and llm_function_core_sanity.txt for quick sanity checks). This duplication allows tests to be run in different testing contexts.
Applied to files:
tests/integration/test_lists/qa/llm_function_rtx6k.txttests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/test-db/l0_gb200_multi_gpus.ymltests/integration/test_lists/waives.txttests/integration/test_lists/qa/llm_function_nim.txttests/integration/test_lists/test-db/l0_dgx_h100.ymltests/integration/test_lists/qa/llm_function_core.txttests/integration/test_lists/qa/llm_function_core_sanity.txttests/integration/test_lists/test-db/l0_dgx_b300.yml
📚 Learning: 2025-09-17T02:48:52.732Z
Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 7781
File: tests/integration/test_lists/waives.txt:313-313
Timestamp: 2025-09-17T02:48:52.732Z
Learning: In TensorRT-LLM, `tests/integration/test_lists/waives.txt` is specifically for waiving/skipping tests, while other test list files like those in `test-db/` and `qa/` directories are for different test execution contexts (pre-merge, post-merge, QA tests). The same test appearing in both waives.txt and execution list files is intentional - the test is part of test suites but will be skipped due to the waiver.
Applied to files:
tests/integration/test_lists/qa/llm_function_rtx6k.txttests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/test-db/l0_gb200_multi_gpus.ymltests/integration/defs/.test_durationstests/integration/test_lists/waives.txttests/integration/test_lists/qa/llm_function_nim.txttests/integration/test_lists/test-db/l0_dgx_h100.ymltests/integration/test_lists/qa/llm_function_core.txttests/integration/test_lists/qa/llm_function_core_sanity.txttests/integration/test_lists/test-db/l0_dgx_b300.yml
📚 Learning: 2025-08-26T09:49:04.956Z
Learnt from: pengbowang-nv
Repo: NVIDIA/TensorRT-LLM PR: 7192
File: tests/integration/test_lists/test-db/l0_dgx_b200.yml:56-72
Timestamp: 2025-08-26T09:49:04.956Z
Learning: In TensorRT-LLM test configuration files, the test scheduling system handles wildcard matching with special rules that prevent duplicate test execution even when the same tests appear in multiple yaml files with overlapping GPU wildcards (e.g., "*b200*" and "*gb200*").
Applied to files:
tests/integration/test_lists/qa/llm_function_rtx6k.txttests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/test-db/l0_gb200_multi_gpus.ymltests/integration/defs/.test_durationstests/integration/test_lists/waives.txttests/integration/test_lists/qa/llm_function_nim.txttests/integration/test_lists/test-db/l0_dgx_h100.ymltests/integration/test_lists/qa/llm_function_core.txttests/integration/test_lists/qa/llm_function_core_sanity.txttests/integration/test_lists/test-db/l0_dgx_b300.yml
📚 Learning: 2025-08-06T13:58:07.506Z
Learnt from: galagam
Repo: NVIDIA/TensorRT-LLM PR: 6487
File: tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py:1-12
Timestamp: 2025-08-06T13:58:07.506Z
Learning: In TensorRT-LLM, test files (files under tests/ directories) do not require NVIDIA copyright headers, unlike production source code files. Test files typically start directly with imports, docstrings, or code.
Applied to files:
tests/integration/test_lists/qa/llm_function_rtx6k.txttests/integration/test_lists/test-db/l0_gb200_multi_gpus.ymltests/integration/test_lists/waives.txttests/integration/test_lists/qa/llm_function_nim.txttests/integration/test_lists/qa/llm_function_core_sanity.txt
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
Repo: NVIDIA/TensorRT-LLM PR: 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:
tests/integration/test_lists/qa/llm_function_rtx6k.txttests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/test-db/l0_gb200_multi_gpus.ymltests/integration/test_lists/waives.txttests/integration/test_lists/qa/llm_function_nim.txttests/integration/test_lists/test-db/l0_dgx_h100.ymltests/integration/test_lists/qa/llm_function_core.txttests/integration/test_lists/qa/llm_function_core_sanity.txttests/integration/test_lists/test-db/l0_dgx_b300.ymltests/integration/defs/accuracy/test_llm_api_pytorch.py
📚 Learning: 2025-11-27T09:23:18.742Z
Learnt from: fredricz-20070104
Repo: NVIDIA/TensorRT-LLM PR: 9511
File: tests/integration/defs/examples/serve/test_serve.py:136-186
Timestamp: 2025-11-27T09:23:18.742Z
Learning: In TensorRT-LLM testing, when adding test cases based on RCCA commands, the command format should be copied exactly as it appears in the RCCA case, even if it differs from existing tests. For example, some RCCA commands for trtllm-serve may omit the "serve" subcommand while others include it.
Applied to files:
tests/integration/test_lists/qa/llm_function_rtx6k.txttests/integration/test_lists/qa/llm_function_core_sanity.txt
📚 Learning: 2025-10-22T06:53:47.017Z
Learnt from: xinhe-nv
Repo: NVIDIA/TensorRT-LLM PR: 8534
File: scripts/format_test_list.py:1-6
Timestamp: 2025-10-22T06:53:47.017Z
Learning: The file `scripts/format_test_list.py` in the TensorRT-LLM repository does not require the NVIDIA Apache-2.0 copyright header.
Applied to files:
tests/integration/test_lists/qa/llm_function_rtx6k.txt
📚 Learning: 2025-08-21T02:39:12.009Z
Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 7104
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu:1475-1480
Timestamp: 2025-08-21T02:39:12.009Z
Learning: The min latency mode functionality in TensorRT-LLM MOE kernels (cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu) is deprecated and no longer being maintained/updated, as confirmed by djns99. Bug reports and optimization suggestions for the computeStridesTmaWarpSpecializedLowLatencyKernel and related min latency code paths should be deprioritized.
Applied to files:
tests/integration/test_lists/qa/llm_function_rtx6k.txt
📚 Learning: 2025-08-22T01:54:35.850Z
Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 7104
File: cpp/tensorrt_llm/kernels/cutlass_kernels/include/moe_kernels.h:999-1000
Timestamp: 2025-08-22T01:54:35.850Z
Learning: The `internal_cutlass_kernels` directory in TensorRT-LLM is a mirror of an internal NVIDIA repository and maintains its own implementation and API that may diverge from the public `cutlass_kernels` version. API inconsistencies between these two directories are intentional and by design, not bugs to be fixed.
Applied to files:
tests/integration/test_lists/qa/llm_function_rtx6k.txt
📚 Learning: 2025-08-11T20:09:24.389Z
Learnt from: achartier
Repo: NVIDIA/TensorRT-LLM PR: 6763
File: tests/integration/defs/triton_server/conftest.py:16-22
Timestamp: 2025-08-11T20:09:24.389Z
Learning: In the TensorRT-LLM test infrastructure, the team prefers simple, direct solutions (like hard-coding directory traversal counts) over more complex but robust approaches when dealing with stable directory structures. They accept the maintenance cost of updating tests if the layout changes.
Applied to files:
tests/integration/test_lists/qa/llm_function_rtx6k.txttests/integration/test_lists/qa/llm_function_core_sanity.txt
📚 Learning: 2025-08-14T23:23:27.449Z
Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 6915
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu:4010-4012
Timestamp: 2025-08-14T23:23:27.449Z
Learning: For MOE (Mixture of Experts) code reviews in TensorRT-LLM, avoid repeatedly suggesting finalize fusion validation checks and safety assertions. The user djns99 has indicated these suggestions are repetitive and unwanted across multiple MOE-related changes.
Applied to files:
tests/integration/test_lists/test-db/l0_gb200_multi_gpus.yml
📚 Learning: 2025-08-29T14:07:45.863Z
Learnt from: EmmaQiaoCh
Repo: NVIDIA/TensorRT-LLM PR: 7370
File: tests/unittest/trt/model_api/test_model_quantization.py:24-27
Timestamp: 2025-08-29T14:07:45.863Z
Learning: In TensorRT-LLM's CI infrastructure, pytest skip markers (pytest.mark.skip) are properly honored even when test files have __main__ blocks that call test functions directly. The testing system correctly skips tests without requiring modifications to the __main__ block execution pattern.
Applied to files:
tests/integration/test_lists/test-db/l0_gb200_multi_gpus.ymltests/integration/test_lists/waives.txttests/integration/test_lists/test-db/l0_dgx_h100.ymltests/integration/defs/accuracy/test_llm_api_pytorch.py
📚 Learning: 2025-08-13T11:07:11.772Z
Learnt from: Funatiq
Repo: NVIDIA/TensorRT-LLM PR: 6754
File: tests/integration/test_lists/test-db/l0_a30.yml:41-47
Timestamp: 2025-08-13T11:07:11.772Z
Learning: In TensorRT-LLM test configuration files like tests/integration/test_lists/test-db/l0_a30.yml, TIMEOUT values are specified in minutes, not seconds.
Applied to files:
tests/integration/test_lists/test-db/l0_gb200_multi_gpus.yml
📚 Learning: 2025-07-22T08:33:49.109Z
Learnt from: yiqingy0
Repo: NVIDIA/TensorRT-LLM PR: 5198
File: jenkins/mergeWaiveList.py:0-0
Timestamp: 2025-07-22T08:33:49.109Z
Learning: In the TensorRT-LLM waive list merging system, removed lines are always located at the end of the merge waive lists, which is why the mergeWaiveList.py script uses reverse traversal - it's an optimization for this specific domain constraint.
Applied to files:
tests/integration/test_lists/waives.txt
📚 Learning: 2025-11-14T11:22:03.729Z
Learnt from: nzmora-nvidia
Repo: NVIDIA/TensorRT-LLM PR: 9163
File: tensorrt_llm/_torch/auto_deploy/custom_ops/quant.py:107-113
Timestamp: 2025-11-14T11:22:03.729Z
Learning: In TensorRT-LLM AutoDeploy custom ops, when adding hardware capability checks to select between kernel implementations (e.g., cuBLAS vs. CUDA kernel), use descriptive variable names that identify the specific GPU architectures or families being targeted (e.g., `is_blackwell_geforce_or_ada`) rather than generic names like `enable_cuda_core`. This makes it clear that the code is selecting an implementation path based on hardware capabilities, not enabling/disabling hardware features.
Applied to files:
tests/integration/test_lists/qa/llm_function_core.txt
📚 Learning: 2025-12-12T10:07:31.564Z
Learnt from: lirundong
Repo: NVIDIA/TensorRT-LLM PR: 9725
File: tensorrt_llm/_torch/custom_ops/cuda_tile_custom_ops.py:110-178
Timestamp: 2025-12-12T10:07:31.564Z
Learning: In PyTorch custom operators registered with torch.library.custom_op, mutable operators that return None and specify mutates_args do not require a register_fake decorator. Mutation tracking is handled automatically without needing a FakeTensor kernel. This applies to Python custom op definitions in tensorrt_llm/_torch/custom_ops that use mutates_args and return None; verify you are not relying on register_fake in these cases.
Applied to files:
tensorrt_llm/_torch/custom_ops/cpp_custom_ops.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
🧬 Code graph analysis (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
tensorrt_llm/llmapi/llm_args.py (2)
CudaGraphConfig(107-164)MoeConfig(443-477)
⏰ 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 (13)
tensorrt_llm/_torch/models/modeling_gpt_oss.py (1)
190-191: No action needed—create_moeaccepts thelayer_idxparameter.The
create_moefunction signature intensorrt_llm/_torch/modules/fused_moe/create_moe.pyincludeslayer_idx: Optional[int] = None, confirming that the addition of'layer_idx': self.layer_idxto themoe_paramsdictionary is valid and will not cause a runtime error.tests/integration/test_lists/qa/llm_function_rtx6k.txt (1)
149-154: LGTM! Systematic test coverage expansion for torch_compile.The expansion from 3 to 6 test entries for 4-GPU configurations is well-structured, adding both eager and torch_compile execution mode variants for each parallelism strategy (dp4, ep4, tp4). This aligns with the PR's objective to add torch_compile support.
tests/integration/test_lists/test-db/l0_dgx_b200.yml (1)
184-189: LGTM! Test updates align with post-merge testing strategy.The test identifiers have been updated to include the
-eagersuffix across multiple parallelism strategies and backends. Note that these test-db configurations only include eager variants (not torch_compile), which is appropriate for hardware-specific post-merge testing where a focused test matrix is preferred.tests/integration/test_lists/test-db/l0_dgx_b300.yml (2)
57-59: LGTM! Post-merge test identifiers updated correctly.The three test entries have been updated to include the
-eagersuffix, covering different backends (cutlass, triton) and quantization modes (fp8, auto). This is consistent with the broader PR pattern of explicitly specifying execution modes.
90-90: LGTM! Pre-merge test identifier updated.The pre-merge test entry has been updated to include the
-eagersuffix for the ep4-trtllm-auto configuration, maintaining consistency with the execution mode specification pattern.tests/integration/test_lists/qa/llm_function_core.txt (1)
590-613: LGTM! Comprehensive test matrix expansion.The 4-GPU test coverage has been systematically expanded from 12 to 24 entries, with each parallelism strategy (dp4, ep4, tp4) and backend combination (cutlass-auto, triton-auto, trtllm-auto, trtllm-fp8) now having both eager and torch_compile execution mode variants. This comprehensive coverage is appropriate for the core QA test list and directly supports the PR's torch_compile feature addition.
tests/integration/test_lists/qa/llm_function_core_sanity.txt (1)
95-118: LGTM! Sanity test list properly mirrors core test expansion.The test matrix expansion here mirrors the comprehensive changes in llm_function_core.txt, with all 4-GPU configurations now having both eager and torch_compile variants. This consistency between core and sanity test lists is intentional and appropriate, allowing quick validation of the full test matrix in different testing contexts.
Based on learnings, this duplication serves different purposes (comprehensive testing vs. quick sanity checks).
tests/integration/test_lists/qa/llm_function_nim.txt (1)
180-203: LGTM! Systematic test expansion for torch_compile support.The expansion of 4-GPU test configurations to include both
-eagerand-torch_compilevariants is well-structured and consistent. Each parallelism mode (dp4, ep4, tp4) combined with different backends (cutlass, triton, trtllm) and precision settings (auto, fp8) now has explicit coverage for both execution modes, which aligns with the PR objective of adding torch_compile support for GPT_OSS.tests/integration/test_lists/waives.txt (1)
304-307: LGTM! Waivers appropriately updated for torch_compile variants.The addition of waivers for eager and torch_compile variants follows the correct format with proper bug references. Note that some waived tests (e.g.,
ep4-cutlass-auto-{eager,torch_compile}anddp4-cutlass-auto-{eager,torch_compile}) also appear in execution lists likel0_gb200_multi_gpus.yml—this is intentional and documented behavior where the waiver takes precedence and the tests will be skipped.Based on learnings, tests can appear in both waives.txt and execution list files when they're part of test suites but need to be skipped due to known issues.
Also applies to: 342-343, 472-475, 481-482
tests/integration/test_lists/test-db/l0_gb200_multi_gpus.yml (2)
56-68: LGTM! GB200 test configurations appropriately expanded.The pre-merge test additions systematically cover eager and torch_compile execution modes for multiple backend configurations (cutlass, triton, trtllm) and parallelism strategies (dp4, ep4, tp4). This expansion is consistent with the changes in other test lists and appropriately targets GB200 hardware validation.
108-113: LGTM! Post-merge enable_configurable_moe variants properly added.The post-merge test additions for
enable_configurable_moeconfigurations with eager and torch_compile modes provide extended coverage for this feature on GB200 hardware. The placement in the post-merge section is appropriate for these more specialized test variants.tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
4110-4111: Torch compile wiring forTestGPTOSS::test_w4_4gpuslooks consistent with existing patternsAdding the
torch_compileparametrization and threadingtorch_compile_config = _get_default_torch_compile_config(torch_compile)throughpytorch_config(alongsideCudaGraphConfigandMoeConfig) matches how torch-compile is plumbed for other models earlier in this file. Pipeline parallel is fixed at 1 in this test matrix, so there’s no conflict with existing “pp + torch.compile” limitations used elsewhere. I don’t see issues here from a test/config perspective.Also applies to: 4130-4168
tests/integration/test_lists/test-db/l0_dgx_h100.yml (1)
203-208: No action needed — YAML node IDs are correctly formatted.The test node IDs in the YAML file are properly constructed and will match pytest's parametrization. Pytest generates node IDs by applying decorators in reverse order (bottom-to-top), resulting in the pattern
[tp/ep/dp_id-moe_backend_id-kv_cache_dtype-torch_compile_id]for theenable_configurable_moe=0case (where that parameter's id is empty and doesn't appear). The entries liketest_w4_4gpus[tp4-cutlass-auto-eager]match this pattern exactly and are correct.Likely an incorrect or invalid review comment.
|
PR_Github #30893 [ run ] completed with state
|
Signed-off-by: Jin Li <[email protected]>
liji-nv
force-pushed
the
dev-liji-gpt-oss-compile
branch
from
cc33f66 to
57cefc6
Compare
|
/bot run |
|
PR_Github #30979 [ run ] triggered by Bot. Commit: |
|
PR_Github #30979 [ run ] completed with state
|
|
/bot run --disable-fail-fast |
|
PR_Github #31034 [ run ] triggered by Bot. Commit: |
|
PR_Github #31034 [ run ] completed with state
|
Signed-off-by: Jin Li <[email protected]>
|
/bot run --disable-fail-fast |
|
PR_Github #31244 [ run ] triggered by Bot. Commit: |
2 participants
Summary by CodeRabbit
New Features
Tests
✏️ Tip: You can customize this high-level summary in your review settings.
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
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.