[None][chore] Final mass integration of release/1.1 #9960
Conversation
mikeiovine
requested review from
HuiGao-NV,
Shixiaowei02,
bmarimuthu-nv and
kaiyux
mikeiovine
force-pushed
the
mass-integrate-1.1
branch
from
30e4893 to
81f6493
Compare
|
/bot run --disable-fail-fast |
mikeiovine
changed the title
📝 WalkthroughWalkthroughAdds dependency installation from constraints.txt to Docker build stages, updates benchmarking and performance documentation with new sections and reorganization, adds Blackwell GPU support details across documentation, introduces TensorRT-LLM Release 1.1 notes, modifies MOE post-quantization logic gating, removes redundant logging, and updates test skip configuration. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~30 minutes
Possibly related PRs
Suggested reviewers
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 |
|
PR_Github #28065 [ run ] triggered by Bot. Commit: |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 11
🧹 Nitpick comments (3)
docker/Dockerfile.multi (1)
94-97: Duplicate dependency install: please justify or dedupe.
Running the samepip3 install -r /tmp/constraints.txttwice likely adds build time and risk; if the second block is required, add a brief comment explaining why, otherwise drop it.docs/source/developer-guide/perf-benchmarking.md (1)
19-37: ToC addition is helpful; consider trimming now-redundant guidance line if you touch this again.
No blocker—just note the doc now points to the serve benchmarking guide multiple times (fine, but a bit repetitive).docs/source/release-notes.md (1)
7-60: Please align tense/labels and tighten wording for release-note readability/consistencyA few small consistency nits in the new 1.1 section:
- Mixed tense: “Add … support” vs “Added … support” (the rest of the file mostly uses past tense).
- Heading label:
- **Benchmark**vs elsewhere- Benchmark:/ “Benchmarks”.Suggested small editorial diff (example—apply consistently across the 1.1 bullets):
-### Key Features and Enhancements +### Key Features and Enhancements - **Model Support** - - Add GPT-OSS model support. - - Add Hunyuan-Dense model support. Thanks to the contribution from @sorenwu. - - Add Hunyuan-MoE model support. Thanks to the contribution from @qianbiaoxiang. - - Add Seed-OSS model support. Thanks to the contribution from @Nekofish-L. + - Added GPT-OSS model support. + - Added Hunyuan-Dense model support. Thanks to the contribution from @sorenwu. + - Added Hunyuan-MoE model support. Thanks to the contribution from @qianbiaoxiang. + - Added Seed-OSS model support. Thanks to the contribution from @Nekofish-L. -- **Benchmark** +- **Benchmarks**
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (14)
docker/Dockerfile.multi(1 hunks)docs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.md(3 hunks)docs/source/developer-guide/perf-benchmarking.md(3 hunks)docs/source/developer-guide/perf-overview.md(6 hunks)docs/source/examples/dynamo_k8s_example.rst(1 hunks)docs/source/features/quantization.md(1 hunks)docs/source/legacy/reference/support-matrix.md(2 hunks)docs/source/models/supported-models.md(1 hunks)docs/source/overview.md(1 hunks)docs/source/release-notes.md(7 hunks)examples/auto_deploy/README.md(1 hunks)tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py(2 hunks)tensorrt_llm/_torch/pyexecutor/py_executor_creator.py(0 hunks)tests/integration/test_lists/waives.txt(0 hunks)
💤 Files with no reviewable changes (2)
- tensorrt_llm/_torch/pyexecutor/py_executor_creator.py
- tests/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 in Python, even if only one class or function from a module is used (e.g., usefrom package.subpackage import fooand thenfoo.SomeClass()instead offrom package.subpackage.foo import SomeClass)
Python filenames should use snake_case (e.g.,some_file.py)
Python class names should use PascalCase (e.g.,class SomeClass)
Python function and method names should use snake_case (e.g.,def my_awesome_function():)
Python local variable names 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
Python comments should be reserved 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 type and description (e.g.,self.x = 5followed by"""<type>: Description of 'x'""")
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 specific errors possible instead of catching all exceptions
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 to implement the logic
Files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
**/*.{cpp,h,cu,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code files should contain an NVIDIA copyright header that includes the current year at the top
Files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
🧠 Learnings (38)
📓 Common learnings
Learnt from: farshadghodsian
Repo: NVIDIA/TensorRT-LLM PR: 7101
File: docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md:36-36
Timestamp: 2025-08-21T00:16:56.457Z
Learning: TensorRT-LLM container release tags in documentation should only reference published NGC container images. The README badge version may be ahead of the actual published container versions.
Learnt from: yibinl-nvidia
Repo: NVIDIA/TensorRT-LLM PR: 6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.
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.
📚 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:
docs/source/legacy/reference/support-matrix.mddocs/source/features/quantization.mddocs/source/overview.md
📚 Learning: 2025-09-23T15:12:38.312Z
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/thop/allreduceOp.cpp:352-446
Timestamp: 2025-09-23T15:12:38.312Z
Learning: In TensorRT-LLM NCCL device implementation, NCCL version 2.28+ requirements are handled at runtime in the nccl_device/config layer rather than with compile-time guards. This allows the allreduceOp to remain version-agnostic and delegates version compatibility validation to the appropriate lower-level components that can gracefully handle unsupported configurations.
Applied to files:
docs/source/legacy/reference/support-matrix.mddocs/source/developer-guide/perf-benchmarking.mddocs/source/overview.mddocs/source/release-notes.md
📚 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:
docs/source/legacy/reference/support-matrix.mddocs/source/overview.mddocs/source/developer-guide/perf-overview.md
📚 Learning: 2025-08-27T14:23:55.566Z
Learnt from: ixlmar
Repo: NVIDIA/TensorRT-LLM PR: 7294
File: tensorrt_llm/_torch/modules/rms_norm.py:17-17
Timestamp: 2025-08-27T14:23:55.566Z
Learning: The TensorRT-LLM project requires Python 3.10+ as evidenced by the use of TypeAlias from typing module, match/case statements, and union type | syntax throughout the codebase, despite some documentation still mentioning Python 3.8+.
Applied to files:
docs/source/legacy/reference/support-matrix.mddocs/source/overview.mddocs/source/release-notes.md
📚 Learning: 2025-08-21T00:16:56.457Z
Learnt from: farshadghodsian
Repo: NVIDIA/TensorRT-LLM PR: 7101
File: docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md:36-36
Timestamp: 2025-08-21T00:16:56.457Z
Learning: TensorRT-LLM container release tags in documentation should only reference published NGC container images. The README badge version may be ahead of the actual published container versions.
Applied to files:
docs/source/legacy/reference/support-matrix.mdexamples/auto_deploy/README.mddocs/source/developer-guide/perf-benchmarking.mddocs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.mddocs/source/overview.mddocs/source/release-notes.md
📚 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:
docs/source/legacy/reference/support-matrix.mddocs/source/features/quantization.mddocs/source/overview.md
📚 Learning: 2025-09-24T03:31:28.908Z
Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 7520
File: tensorrt_llm/_torch/pyexecutor/resource_manager.py:605-613
Timestamp: 2025-09-24T03:31:28.908Z
Learning: In TensorRT-LLM Ray orchestrator mode, ProcessGroups are initialized with both Gloo and NCCL backends (e.g., "cuda:nccl,cpu:gloo"), allowing PyTorch distributed to automatically route CPU tensors through Gloo and GPU tensors through NCCL. This eliminates the need for manual device placement when performing allreduce operations on base types.
Applied to files:
docs/source/legacy/reference/support-matrix.md
📚 Learning: 2025-09-19T21:28:13.751Z
Learnt from: jhaotingc
Repo: NVIDIA/TensorRT-LLM PR: 7856
File: cpp/tensorrt_llm/thop/fp8BlockScaleMoe.cpp:159-166
Timestamp: 2025-09-19T21:28:13.751Z
Learning: In TensorRT-LLM blockScaleMoe routing (cpp/tensorrt_llm/kernels/trtllmGenKernels/blockScaleMoe/runner.cu), the DeepSeek routing method performs reinterpret_cast<float*>(routingLogits) at line 89, which could cause issues if routing_logits are BF16. However, Qwen3-FP8 models use RenormalizeNaive routing method and are not affected by this dtype casting issue.
Applied to files:
docs/source/legacy/reference/support-matrix.mdtensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
📚 Learning: 2025-08-06T03:47:16.802Z
Learnt from: venkywonka
Repo: NVIDIA/TensorRT-LLM PR: 6650
File: tests/integration/test_lists/qa/llm_perf_cluster.yml:33-37
Timestamp: 2025-08-06T03:47:16.802Z
Learning: Ministral is a valid and distinct model family from Mistral AI, separate from their regular Mistral models. Ministral 8B is specifically designed for edge computing and on-device applications, released in October 2024. In TensorRT-LLM test configurations, "ministral_8b" and "ministral_8b_fp8" are correct model identifiers and should not be changed to "mistral_8b".
Applied to files:
docs/source/legacy/reference/support-matrix.md
📚 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:
docs/source/developer-guide/perf-benchmarking.mddocs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.mddocs/source/developer-guide/perf-overview.mddocs/source/release-notes.md
📚 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:
docs/source/developer-guide/perf-benchmarking.mddocs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.mddocs/source/developer-guide/perf-overview.mddocs/source/release-notes.md
📚 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:
docs/source/developer-guide/perf-benchmarking.mddocs/source/developer-guide/perf-overview.mddocs/source/release-notes.md
📚 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:
docs/source/developer-guide/perf-benchmarking.mddocs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.mddocs/source/developer-guide/perf-overview.md
📚 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:
docs/source/developer-guide/perf-benchmarking.mddocs/source/developer-guide/perf-overview.mddocs/source/release-notes.md
📚 Learning: 2025-08-18T08:42:02.640Z
Learnt from: samuellees
Repo: NVIDIA/TensorRT-LLM PR: 6974
File: tensorrt_llm/serve/scripts/benchmark_dataset.py:558-566
Timestamp: 2025-08-18T08:42:02.640Z
Learning: In TensorRT-LLM's RandomDataset (tensorrt_llm/serve/scripts/benchmark_dataset.py), when using --random-token-ids option, sequence length accuracy is prioritized over semantic correctness for benchmarking purposes. The encode/decode operations should use skip_special_tokens=True and add_special_tokens=False to ensure exact target token lengths.
Applied to files:
docs/source/developer-guide/perf-benchmarking.mddocs/source/developer-guide/perf-overview.md
📚 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:
docs/source/developer-guide/perf-benchmarking.mddocs/source/developer-guide/perf-overview.md
📚 Learning: 2025-08-01T15:14:45.673Z
Learnt from: yibinl-nvidia
Repo: NVIDIA/TensorRT-LLM PR: 6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.
Applied to files:
docs/source/developer-guide/perf-benchmarking.mddocs/source/developer-guide/perf-overview.mddocs/source/release-notes.md
📚 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:
docs/source/developer-guide/perf-benchmarking.mddocs/source/developer-guide/perf-overview.md
📚 Learning: 2025-08-09T02:04:49.623Z
Learnt from: Fridah-nv
Repo: NVIDIA/TensorRT-LLM PR: 6760
File: tensorrt_llm/_torch/auto_deploy/models/quant_config_reader.py:81-98
Timestamp: 2025-08-09T02:04:49.623Z
Learning: In TensorRT-LLM's auto_deploy module, torch.dtype values in configuration dictionaries must be stored as string representations (e.g., "float16" instead of torch.float16) because OmegaConf.merge does not support torch.dtype types. These string representations are converted to actual torch.dtype objects in downstream code.
Applied to files:
docs/source/developer-guide/perf-benchmarking.md
📚 Learning: 2025-08-20T15:04:42.885Z
Learnt from: dbari
Repo: NVIDIA/TensorRT-LLM PR: 7095
File: docker/Dockerfile.multi:168-168
Timestamp: 2025-08-20T15:04:42.885Z
Learning: In docker/Dockerfile.multi, wildcard COPY for benchmarks (${CPP_BUILD_DIR}/benchmarks/*Benchmark) is intentionally used instead of directory copy because the benchmarks directory contains various other build artifacts during C++ builds, and only specific benchmark executables should be copied to the final image.
Applied to files:
docker/Dockerfile.multi
📚 Learning: 2025-08-08T22:03:40.707Z
Learnt from: sklevtsov-nvidia
Repo: NVIDIA/TensorRT-LLM PR: 3294
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu:1198-1209
Timestamp: 2025-08-08T22:03:40.707Z
Learning: In the CUTLASS MoE kernels (cpp/tensorrt_llm/cutlass_extensions), when `layout_info.fusion` is set to `TmaWarpSpecializedGroupedGemmInput::EpilogueFusion::FINALIZE`, the `router_scales` parameter must be non-null by design. The fused finalize kernel epilogue does not perform nullptr checks and requires valid router scales to function correctly. This is an implicit contract that callers must satisfy when enabling the FINALIZE fusion mode.
Applied to files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
📚 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:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
📚 Learning: 2025-08-19T03:35:20.866Z
Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 6915
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu:4616-4626
Timestamp: 2025-08-19T03:35:20.866Z
Learning: In the MOE profiler TMA workspace preparation (cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu), the overlapping of TMA WS regions for NONE and FINALIZE variants is deliberate design to save memory space, as confirmed by djns99. The comment "reuse the same pointers to save space" reflects this intentional behavior.
Applied to files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
📚 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:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.pydocs/source/release-notes.md
📚 Learning: 2025-08-09T20:57:04.084Z
Learnt from: sklevtsov-nvidia
Repo: NVIDIA/TensorRT-LLM PR: 3294
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_gemm_tma_warp_specialized_input.cu:118-127
Timestamp: 2025-08-09T20:57:04.084Z
Learning: In the CUTLASS MoE finalize fusion implementation (cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_gemm_tma_warp_specialized_input.cu), when setting `fused_finalize_epilogue.stride_final_output` with shape `(hidden_size, num_output_tokens, 1)`, the `num_rows_in_final_output` should be set to `num_output_tokens` (not `hidden_size`) because of a swap+transpose operation that maps rows of the output tensor to `hidden_size` and columns to `num_output_tokens`.
Applied to files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
📚 Learning: 2025-09-23T15:12:38.312Z
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/thop/allreduceOp.cpp:352-446
Timestamp: 2025-09-23T15:12:38.312Z
Learning: In TensorRT-LLM NCCL device allreduce implementation (cpp/tensorrt_llm/thop/allreduceOp.cpp), the goto pattern in runNCCLAllReduceDeviceFusion is intentionally used for future extensibility, allowing multiple switch cases to fallback to the default handler. While not aesthetically ideal, this pattern supports adding more fusion cases later that can reuse the same fallback logic.
Applied to files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
📚 Learning: 2025-08-19T12:45:11.997Z
Learnt from: amitz-nv
Repo: NVIDIA/TensorRT-LLM PR: 7033
File: tensorrt_llm/_torch/pyexecutor/model_engine.py:0-0
Timestamp: 2025-08-19T12:45:11.997Z
Learning: In tensorrt_llm/_torch/pyexecutor/model_engine.py, DoRA (Delta Orthogonal Rank Adaptation) functionality was removed from the PyTorch flow to eliminate issues with inverted DoRA detection logic. The original is_dora condition was checking if scaling_vec_pointer == 0, which was potentially incorrect.
Applied to files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.pydocs/source/release-notes.md
📚 Learning: 2025-10-20T17:07:18.745Z
Learnt from: nvchenghaoz
Repo: NVIDIA/TensorRT-LLM PR: 8469
File: tensorrt_llm/_torch/auto_deploy/models/patches/nemotron_h.py:98-116
Timestamp: 2025-10-20T17:07:18.745Z
Learning: In NemotronH models (tensorrt_llm/_torch/auto_deploy/models/patches/nemotron_h.py), the gate (self.gate) returns topk_indices and topk_weights that are already in the correct shape to be passed directly to torch_ops.auto_deploy.torch_moe without needing to reshape them when hidden_states is flattened.
Applied to files:
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py
📚 Learning: 2025-09-18T05:41:45.847Z
Learnt from: pengbowang-nv
Repo: NVIDIA/TensorRT-LLM PR: 7120
File: tensorrt_llm/llmapi/llm.py:690-697
Timestamp: 2025-09-18T05:41:45.847Z
Learning: Kimi model support is currently focused on the PyTorch backend path, with TRT path support potentially coming later.
Applied to files:
docs/source/overview.md
📚 Learning: 2025-11-24T17:09:17.870Z
Learnt from: CR
Repo: NVIDIA/TensorRT-LLM PR: 0
File: CODING_GUIDELINES.md:0-0
Timestamp: 2025-11-24T17:09:17.870Z
Learning: Applies to **/*.py : The code developed for TensorRT-LLM should conform to Python 3.8+
Applied to files:
docs/source/overview.md
📚 Learning: 2025-08-20T07:43:36.447Z
Learnt from: ChristinaZ
Repo: NVIDIA/TensorRT-LLM PR: 7068
File: cpp/tensorrt_llm/kernels/moeTopKFuncs.cuh:169-172
Timestamp: 2025-08-20T07:43:36.447Z
Learning: In TensorRT-LLM MOE kernels, when processing up to 128 experts across 32 threads, each thread handles at most 4 experts (N < 5 constraint), where N represents candidates per thread rather than total system capacity.
Applied to files:
docs/source/developer-guide/perf-overview.md
📚 Learning: 2025-09-09T18:31:44.336Z
Learnt from: venkywonka
Repo: NVIDIA/TensorRT-LLM PR: 7658
File: .github/CODEOWNERS:160-164
Timestamp: 2025-09-09T18:31:44.336Z
Learning: The ruleset for `release/**` branch patterns in the NVIDIA/TensorRT-LLM repository covers NIM-specific release branches like `release/1.0.1-NIM`, ensuring proper code ownership enforcement.
Applied to files:
docs/source/release-notes.md
📚 Learning: 2025-10-17T13:21:31.724Z
Learnt from: ixlmar
Repo: NVIDIA/TensorRT-LLM PR: 8398
File: tensorrt_llm/_torch/pyexecutor/sampling_utils.py:237-272
Timestamp: 2025-10-17T13:21:31.724Z
Learning: The setup.py file in TensorRT-LLM explicitly requires Python 3.10+ via `python_requires=">=3.10, <4"`, making match/case statements and other Python 3.10+ features appropriate throughout the codebase.
Applied to files:
docs/source/release-notes.md
📚 Learning: 2025-08-26T06:07:02.166Z
Learnt from: shaharmor98
Repo: NVIDIA/TensorRT-LLM PR: 7231
File: tensorrt_llm/_torch/pyexecutor/_util.py:504-509
Timestamp: 2025-08-26T06:07:02.166Z
Learning: In tensorrt_llm/_torch/pyexecutor/_util.py, when calling model_engine.set_lora_model_config(), pass model_binding_config.mlp_hidden_size directly without multiplying by mapping.tp_size, as the mlp_hidden_size from get_bindings_model_config() is already the per-TP rank value needed for LoRA weight packaging.
Applied to files:
docs/source/release-notes.md
📚 Learning: 2025-07-17T09:01:27.402Z
Learnt from: amitz-nv
Repo: NVIDIA/TensorRT-LLM PR: 5616
File: tensorrt_llm/executor/worker.py:375-384
Timestamp: 2025-07-17T09:01:27.402Z
Learning: In tensorrt_llm/executor/worker.py, the LoRA adapter cache optimization logic that checks `is_adapter_in_cpu_cache()` and conditionally passes None for weights/config has a known race condition issue that cannot be solved with simple error handling or verification checks. This is a known limitation that requires a more comprehensive solution.
Applied to files:
docs/source/release-notes.md
📚 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:
docs/source/release-notes.md
📚 Learning: 2025-08-14T15:43:23.107Z
Learnt from: MatthiasKohl
Repo: NVIDIA/TensorRT-LLM PR: 6904
File: tensorrt_llm/_torch/attention_backend/trtllm.py:259-262
Timestamp: 2025-08-14T15:43:23.107Z
Learning: In TensorRT-LLM's attention backend, tensor parameters in the plan() method are assigned directly without validation (dtype, device, contiguity checks). This maintains consistency across all tensor inputs and follows the pattern of trusting callers to provide correctly formatted tensors.
Applied to files:
docs/source/release-notes.md
🧬 Code graph analysis (1)
tensorrt_llm/_torch/modules/fused_moe/fused_moe_trtllm_gen.py (3)
tensorrt_llm/_torch/modules/fused_moe/interface.py (1)
has_deepseek_fp8_block_scales(681-684)tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py (2)
fp8_block_scale_moe_runner(677-756)bf16_mxe2m1_block_scale_moe_runner(1517-1610)tensorrt_llm/_torch/modules/fused_moe/configurable_moe.py (1)
w3_w1_weight(1103-1105)
🪛 LanguageTool
docs/source/developer-guide/perf-benchmarking.md
[grammar] ~12-~12: Use a hyphen to join words.
Context: ...m-serve` command, which starts an OpenAI compatible server that supports the foll...
(QB_NEW_EN_HYPHEN)
🪛 markdownlint-cli2 (0.18.1)
docs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.md
23-23: Unordered list indentation
Expected: 4; Actual: 6
(MD007, ul-indent)
24-24: Unordered list indentation
Expected: 4; Actual: 6
(MD007, ul-indent)
25-25: Unordered list indentation
Expected: 4; Actual: 6
(MD007, ul-indent)
26-26: Unordered list indentation
Expected: 4; Actual: 6
(MD007, ul-indent)
docs/source/developer-guide/perf-overview.md
156-156: Emphasis used instead of a heading
(MD036, no-emphasis-as-heading)
207-207: Emphasis used instead of a heading
(MD036, no-emphasis-as-heading)
241-241: Emphasis used instead of a heading
(MD036, no-emphasis-as-heading)
⏰ 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)
examples/auto_deploy/README.md (1)
93-99: Terminology update looks good.The change from generic "Model Optimizer" to "TensorRT Model Optimizer" aligns with the PR's documentation standardization effort. The hyperlink remains valid and the AutoQuantize explanation is accurate and clear.
docs/source/legacy/reference/support-matrix.md (2)
133-142: Verify GB300 NVL72 naming + link stability (avoid stale marketing URLs).
Since this is a legacy support matrix, please double-check the “GB300 NVL72” product name and that the URL is the intended long-lived reference (marketing URLs sometimes move).
159-165: Confirm SM103 inclusion and scope for Blackwell precision list.
The addition of SM103 expands the documented precision support surface; please verify it matches the actual supported SMs for Blackwell in TensorRT-LLM 1.1 (and aligns with other docs in this PR).docs/source/models/supported-models.md (1)
44-45: Please validate the SM eligibility notes match actual feature gating.
These footnotes expand hardware eligibility (SM103); make sure this matches the implementation (and any existing constraints in release/1.1).docs/source/examples/dynamo_k8s_example.rst (1)
4-7: Verify the Dynamo Quick Start URL is a stable permalink.
Given docs paths can change, please confirm this exact URL is correct/current and prefer the most stable entrypoint if NVIDIA docs provide one.docker/Dockerfile.multi (1)
74-77:constraints.txtinstalled via-r: confirm this is intended semantics.
If this file is truly a constraints file, consider switching topip install -c /tmp/constraints.txt -r requirements.txt(or rename torequirements-*.txtif it’s the definitive pinned set).docs/source/overview.md (1)
56-60: Please verify product naming + FP4 optimization claim scope.
Ensure the Blackwell bullet (B300/GB300/RTX Pro 6000 SE FP4) matches what TRT-LLM 1.1 actually supports and what you’re comfortable claiming publicly.docs/source/features/quantization.md (2)
121-130: Confirm SM103 quantization capability claims in the hardware matrix.
AddingBlackwell(sm100/103)broadens stated support—please verify it matches actual kernel availability and any internal gating.
131-133: Verify the MXFP8 recipe note is technically precise for sm100/103.
This is a low-level statement about recipes/scales; worth double-checking against the implementation/docs you’re sourcing from.docs/source/commands/trtllm-serve/run-benchmark-with-trtllm-serve.md (1)
38-41: Doc restructure reads well; please keep container tags pointing to published NGC images.
The new “Preparation / Start / Benchmark” layout is clearer. Just ensure any non-placeholder container tags used elsewhere in this doc (or adjacent docs) only reference actually published NGC tags. Based on learnings, container tag versions in docs can get ahead of what’s published.Also applies to: 51-56, 101-104
docs/source/developer-guide/perf-benchmarking.md (1)
444-445: Cross-linking to ModelOpt + serve benchmarking guide looks good.
The updated ModelOpt link and the new Online Serving Benchmarking pointer improve discoverability.Also applies to: 489-493
docs/source/release-notes.md (2)
119-120: Spot-check these single-line edits for unintended doc drift vs release/1.1These look like small touch-ups, but given this is a mass-integration PR, please sanity-check they exactly match release/1.1 intent (no accidental cherry-pick drift):
- Line 119-120 (LoRA bullet)
- Line 158-159 (KV cache reuse for multimodal)
- Line 217-218 (API removal bullets)
- Line 276-277 (known issue)
Suggested quick “compare to release branch” action: confirm these exact lines match
release/1.1(or are intentional main-only deltas).Also applies to: 158-159, 217-218, 276-277
54-61: NGC tags and dependency versions are accurate and published.Verification confirms both NGC base images (
nvcr.io/nvidia/pytorch:25.10-py3andnvcr.io/nvidia/tritonserver:25.10-py3) are published. All Python dependencies matchrequirements.txt: PyTorch 2.9.0, ModelOpt 0.37, transformers 4.56.0, and xgrammar 0.1.25 are correctly pinned. NIXL 0.5.0 is a system-level dependency handled via build configuration rather than Python requirements.
|
PR_Github #28065 [ run ] completed with state |
mikeiovine
force-pushed
the
mass-integrate-1.1
branch
from
81f6493 to
2adf10c
Compare
|
/bot run --disable-fail-fast |
mikeiovine
force-pushed
the
mass-integrate-1.1
branch
from
2adf10c to
dbbd89f
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #28113 [ run ] triggered by Bot. Commit: |
|
PR_Github #28114 [ run ] triggered by Bot. Commit: |
|
PR_Github #28113 [ run ] completed with state |
|
PR_Github #28114 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #28419 [ run ] triggered by Bot. Commit: |
|
PR_Github #28419 [ run ] completed with state |
|
/bot run --disable-fail-fast |
|
PR_Github #28444 [ run ] triggered by Bot. Commit: |
|
PR_Github #28444 [ run ] completed with state |
mikeiovine
force-pushed
the
mass-integrate-1.1
branch
from
a7a2d80 to
8866243
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #28453 [ run ] triggered by Bot. Commit: |
|
PR_Github #28453 [ run ] completed with state |
mikeiovine
force-pushed
the
mass-integrate-1.1
branch
from
8866243 to
a92d96e
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #28508 [ run ] triggered by Bot. Commit: |
|
PR_Github #28508 [ run ] completed with state |
Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>
Signed-off-by: Iman Tabrizian <10105175+tabrizian@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>
…VIDIA#9206) Signed-off-by: Ruodi Lu <ruodil@users.noreply.github.com> Co-authored-by: Ruodi Lu <ruodil@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>
…Release 1.1 (NVIDIA#9723) Signed-off-by: Zachary Patel <22306219+zbpatel@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com> Signed-off-by: QI JUN <22017000+QiJune@users.noreply.github.com> Co-authored-by: Laikh Tewari <laikhtewari1@gmail.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>
Signed-off-by: junq <22017000+QiJune@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>
…9887) Signed-off-by: junq <22017000+QiJune@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>
mikeiovine
force-pushed
the
mass-integrate-1.1
branch
from
a92d96e to
f865ed7
Compare
|
/bot skip --comment "Docs only" |
|
Looks like it was already merged to main: #8008 |
|
PR_Github #28597 [ skip ] triggered by Bot. Commit: |
|
PR_Github #28597 [ skip ] completed with state |
13 participants
Description
PRs excluded:
Test Coverage
N/A
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.
Summary by CodeRabbit
New Features
Documentation
Infrastructure
✏️ Tip: You can customize this high-level summary in your review settings.