[TRTLLM-14026][feat] BREAKING: Remove C++ modules for legacy TRT backend

.claude/skills/exec-local-compile/SKILL.md

@@ -45,7 +45,7 @@ git checkout main && git pull
 Run the build command (**incremental by default** — omit `-c`/`--clean` unless explicitly requested or the incremental build fails):
 
 ```bash
-./scripts/build_wheel.py --trt_root /usr/local/tensorrt --benchmarks --use_ccache -a "<arch>" -f --nvtx
+./scripts/build_wheel.py --trt_root /usr/local/tensorrt --use_ccache -a "<arch>" -f --nvtx
 ```
 
 Replace `<arch>` with the target GPU architecture (see Architecture Reference below). If not specified by the user, auto-detect from `nvidia-smi`.
@@ -67,7 +67,6 @@ python3 -c "import tensorrt_llm; print(tensorrt_llm.__version__)"
 | Flag | Description |
 |------|-------------|
 | `--trt_root /usr/local/tensorrt` | TensorRT installation path (standard in NVIDIA containers) |
-| `--benchmarks` | Build the C++ benchmarks |
 | `-a "<arch>"` | Target GPU architecture(s) |
 | `--nvtx` | Enable NVTX markers for profiling |
 | `--use_ccache` | Use ccache for faster recompilation |

.claude/skills/exec-slurm-compile/SKILL.md

@@ -205,7 +205,6 @@ A successful build ends with a message like `Successfully built tensorrt_llm` or
 | Flag | Description |
 |------|-------------|
 | `--trt_root /usr/local/tensorrt` | TensorRT installation path (standard in NVIDIA containers) |
-| `--benchmarks` | Build the C++ benchmarks |
 | `-a "100-real"` | Target architecture — `100` for Blackwell, `90` for Hopper, etc. |
 | `--nvtx` | Enable NVTX markers for profiling |
 | `--no-venv` | Skip virtual environment creation |

.claude/skills/exec-slurm-compile/scripts/compile.sh

@@ -19,7 +19,7 @@
 # Usage: compile.sh <repo_dir> [build_wheel_args...]
 #
 # Default build_wheel.py flags:
-#   --trt_root /usr/local/tensorrt --benchmarks -a "100-real" --nvtx --no-venv
+#   --trt_root /usr/local/tensorrt -a "100-real" --nvtx --no-venv
 # Any extra arguments after repo_dir are forwarded to build_wheel.py,
 # overriding the defaults above.
 
@@ -37,7 +37,6 @@ else
     echo "[compile.sh] Running default build command"
     python3 ./scripts/build_wheel.py \
         --trt_root /usr/local/tensorrt \
-        --benchmarks \
         -a "100-real" \
         --nvtx
 fi

.github/CODEOWNERS

@@ -37,8 +37,6 @@
 /tests/unittest @NVIDIA/trt-llm-devs
 
 # ===== TensorRT backend (will be deprecated soon) — also on the trt-llm-devs fallback =====
-/cpp/include/tensorrt_llm/plugins @NVIDIA/trt-llm-devs
-/cpp/tensorrt_llm/plugins @NVIDIA/trt-llm-devs
 /tensorrt_llm/builder.py @NVIDIA/trt-llm-devs
 /tensorrt_llm/commands/build.py @NVIDIA/trt-llm-devs
 /tensorrt_llm/commands/prune.py @NVIDIA/trt-llm-devs
@@ -105,7 +103,6 @@
 /cpp/tensorrt_llm/batch_manager @NVIDIA/trt-llm-runtime-devs
 /cpp/tensorrt_llm/common @NVIDIA/trt-llm-runtime-devs
 /cpp/tensorrt_llm/executor @NVIDIA/trt-llm-runtime-devs
-/cpp/tensorrt_llm/executor_worker @NVIDIA/trt-llm-runtime-devs
 /cpp/tensorrt_llm/layers @NVIDIA/trt-llm-runtime-devs
 /cpp/tensorrt_llm/nanobind @NVIDIA/trt-llm-runtime-devs
 /cpp/tensorrt_llm/runtime @NVIDIA/trt-llm-runtime-devs
@@ -169,7 +166,6 @@
 /examples/llm-api/quickstart_multimodal.py @NVIDIA/trt-llm-models-devs @NVIDIA/trt-llm-doc-owners
 /examples/models @NVIDIA/trt-llm-models-devs @NVIDIA/trt-llm-doc-owners
 /examples/serve/*multimodal* @NVIDIA/trt-llm-models-devs @NVIDIA/trt-llm-doc-owners
-/scripts/build_cpp_examples.py @NVIDIA/trt-llm-models-devs
 /scripts/generate_config_database_tests.py @NVIDIA/trt-llm-models-devs @NVIDIA/trt-llm-doc-owners
 /scripts/generate_config_table.py @NVIDIA/trt-llm-models-devs @NVIDIA/trt-llm-doc-owners
 /tensorrt_llm/_torch/models @NVIDIA/trt-llm-models-devs

.pre-commit-config.yaml

@@ -9,14 +9,14 @@ common-files: &common_files |
         .devcontainer/make_env.py |
         .github/scripts/label_community_user.py |
         .github/scripts/pr_checklist_check.py |
-        benchmarks/cpp/__init__.py |
-        benchmarks/cpp/prepare_dataset.py |
-        benchmarks/cpp/utils/__init__.py |
-        benchmarks/cpp/utils/convert_nemo_dataset.py |
-        benchmarks/cpp/utils/generate_rand_loras.py |
-        benchmarks/cpp/utils/prepare_real_data.py |
-        benchmarks/cpp/utils/prepare_synthetic_data.py |
-        benchmarks/cpp/utils/utils.py |
+        benchmarks/__init__.py |
+        benchmarks/prepare_dataset.py |
+        benchmarks/utils/__init__.py |
+        benchmarks/utils/convert_nemo_dataset.py |
+        benchmarks/utils/generate_rand_loras.py |
+        benchmarks/utils/prepare_real_data.py |
+        benchmarks/utils/prepare_synthetic_data.py |
+        benchmarks/utils/utils.py |
         cpp/conanfile.py |
         cpp/kernels/fmha_v2/conftest.py |
         cpp/kernels/fmha_v2/fmha_test.py |
@@ -41,38 +41,11 @@ common-files: &common_files |
         cpp/tensorrt_llm/deep_ep/strip_nvshmem_helper.py |
         cpp/tensorrt_llm/kernels/cutlass_kernels/python/generate_kernels.py |
         cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/copy_cu.py |
-        cpp/tests/resources/scripts/build_chatglm_engines.py |
-        cpp/tests/resources/scripts/build_eagle_engines.py |
-        cpp/tests/resources/scripts/build_enc_dec_engines.py |
-        cpp/tests/resources/scripts/build_engines_utils.py |
-        cpp/tests/resources/scripts/build_gpt_engines.py |
-        cpp/tests/resources/scripts/build_gptj_engines.py |
-        cpp/tests/resources/scripts/build_llama_engines.py |
-        cpp/tests/resources/scripts/build_mamba_engines.py |
-        cpp/tests/resources/scripts/build_medusa_engines.py |
-        cpp/tests/resources/scripts/build_recurrentgemma_engines.py |
-        cpp/tests/resources/scripts/build_redrafter_engines.py |
-        cpp/tests/resources/scripts/generate_expected_chatglm_output.py |
-        cpp/tests/resources/scripts/generate_expected_eagle_output.py |
-        cpp/tests/resources/scripts/generate_expected_enc_dec_output.py |
-        cpp/tests/resources/scripts/generate_expected_gpt_output.py |
-        cpp/tests/resources/scripts/generate_expected_gptj_output.py |
-        cpp/tests/resources/scripts/generate_expected_llama_output.py |
-        cpp/tests/resources/scripts/generate_expected_mamba_output.py |
-        cpp/tests/resources/scripts/generate_expected_medusa_output.py |
-        cpp/tests/resources/scripts/generate_expected_recurrentgemma_output.py |
-        cpp/tests/resources/scripts/generate_expected_redrafter_output.py |
-        cpp/tests/resources/scripts/generate_hf_gpt_output.py |
         cpp/tests/resources/scripts/generate_test_lora_weights.py |
-        cpp/tests/resources/scripts/io_converter.py |
         docs/source/conf.py |
         docs/source/helper.py |
         examples/apps/chat.py |
         examples/apps/fastapi_server.py |
-        examples/bindings/executor/example_advanced.py |
-        examples/bindings/executor/example_basic.py |
-        examples/bindings/executor/example_debug.py |
-        examples/bindings/executor/example_logits_processor.py |
         examples/disaggregated/clients/disagg_client.py |
         examples/disaggregated/slurm/benchmark/submit.py |
         examples/dora/normalize_weights.py |
@@ -246,7 +219,6 @@ common-files: &common_files |
         jenkins/scripts/mergeWaiveList.py |
         jenkins/scripts/open_search_db.py |
         jenkins/scripts/test_rerun.py |
-        scripts/build_cpp_examples.py |
         scripts/build_wheel.py |
         scripts/check_test_list.py |
         scripts/dco_check.py |
@@ -851,11 +823,8 @@ common-files: &common_files |
         tests/integration/defs/conftest.py |
         tests/integration/defs/cpp/conftest.py |
         tests/integration/defs/cpp/cpp_common.py |
-        tests/integration/defs/cpp/test_e2e.py |
         tests/integration/defs/cpp/test_multi_gpu.py |
         tests/integration/defs/cpp/test_unit_tests.py |
-        tests/integration/defs/deterministic/mixtral_deterministic.py |
-        tests/integration/defs/deterministic/test_mixtral_deterministic.py |
         tests/integration/defs/disaggregated/test_auto_scaling.py |
         tests/integration/defs/disaggregated/test_disaggregated.py |
         tests/integration/defs/disaggregated/test_disaggregated_etcd.py |
@@ -928,7 +897,6 @@ common-files: &common_files |
         tests/integration/defs/test_fmha.py |
         tests/integration/defs/test_list_parser.py |
         tests/integration/defs/test_list_validation.py |
-        tests/integration/defs/test_mlpf_results.py |
         tests/integration/defs/test_sanity.py |
         tests/integration/defs/test_unittests.py |
         tests/integration/defs/triton_server/__init__.py |
@@ -1081,7 +1049,6 @@ common-files: &common_files |
         tests/unittest/_torch/thop/serial/test_moe_alltoall.py |
         tests/unittest/api_stability/api_stability_core.py |
         tests/unittest/api_stability/test_llm_api.py |
-        tests/unittest/bindings/binding_test_utils.py |
         tests/unittest/bindings/test_bindings_moe.py |
         tests/unittest/bindings/test_bindings_ut.py |
         tests/unittest/bindings/test_executor_bindings.py |
@@ -1169,7 +1136,6 @@ common-files: &common_files |
         tests/unittest/others/test_kv_cache_transceiver.py |
         tests/unittest/others/test_kv_cache_update.py |
         tests/unittest/others/test_layer.py |
-        tests/unittest/others/test_leak.py |
         tests/unittest/others/test_mapping.py |
         tests/unittest/others/test_model_dtype.py |
         tests/unittest/others/test_module.py |
@@ -1350,14 +1316,14 @@ legacy-files: &legacy_files |
         .devcontainer/make_env.py |
         .github/scripts/label_community_user.py |
         .github/scripts/pr_checklist_check.py |
-        benchmarks/cpp/__init__.py |
-        benchmarks/cpp/prepare_dataset.py |
-        benchmarks/cpp/utils/__init__.py |
-        benchmarks/cpp/utils/convert_nemo_dataset.py |
-        benchmarks/cpp/utils/generate_rand_loras.py |
-        benchmarks/cpp/utils/prepare_real_data.py |
-        benchmarks/cpp/utils/prepare_synthetic_data.py |
-        benchmarks/cpp/utils/utils.py |
+        benchmarks/__init__.py |
+        benchmarks/prepare_dataset.py |
+        benchmarks/utils/__init__.py |
+        benchmarks/utils/convert_nemo_dataset.py |
+        benchmarks/utils/generate_rand_loras.py |
+        benchmarks/utils/prepare_real_data.py |
+        benchmarks/utils/prepare_synthetic_data.py |
+        benchmarks/utils/utils.py |
         cpp/conanfile.py |
         cpp/kernels/fmha_v2/conftest.py |
         cpp/kernels/fmha_v2/fmha_test.py |
@@ -1382,38 +1348,11 @@ legacy-files: &legacy_files |
         cpp/tensorrt_llm/deep_ep/strip_nvshmem_helper.py |
         cpp/tensorrt_llm/kernels/cutlass_kernels/python/generate_kernels.py |
         cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/copy_cu.py |
-        cpp/tests/resources/scripts/build_chatglm_engines.py |
-        cpp/tests/resources/scripts/build_eagle_engines.py |
-        cpp/tests/resources/scripts/build_enc_dec_engines.py |
-        cpp/tests/resources/scripts/build_engines_utils.py |
-        cpp/tests/resources/scripts/build_gpt_engines.py |
-        cpp/tests/resources/scripts/build_gptj_engines.py |
-        cpp/tests/resources/scripts/build_llama_engines.py |
-        cpp/tests/resources/scripts/build_mamba_engines.py |
-        cpp/tests/resources/scripts/build_medusa_engines.py |
-        cpp/tests/resources/scripts/build_recurrentgemma_engines.py |
-        cpp/tests/resources/scripts/build_redrafter_engines.py |
-        cpp/tests/resources/scripts/generate_expected_chatglm_output.py |
-        cpp/tests/resources/scripts/generate_expected_eagle_output.py |
-        cpp/tests/resources/scripts/generate_expected_enc_dec_output.py |
-        cpp/tests/resources/scripts/generate_expected_gpt_output.py |
-        cpp/tests/resources/scripts/generate_expected_gptj_output.py |
-        cpp/tests/resources/scripts/generate_expected_llama_output.py |
-        cpp/tests/resources/scripts/generate_expected_mamba_output.py |
-        cpp/tests/resources/scripts/generate_expected_medusa_output.py |
-        cpp/tests/resources/scripts/generate_expected_recurrentgemma_output.py |
-        cpp/tests/resources/scripts/generate_expected_redrafter_output.py |
-        cpp/tests/resources/scripts/generate_hf_gpt_output.py |
         cpp/tests/resources/scripts/generate_test_lora_weights.py |
-        cpp/tests/resources/scripts/io_converter.py |
         docs/source/conf.py |
         docs/source/helper.py |
         examples/apps/chat.py |
         examples/apps/fastapi_server.py |
-        examples/bindings/executor/example_advanced.py |
-        examples/bindings/executor/example_basic.py |
-        examples/bindings/executor/example_debug.py |
-        examples/bindings/executor/example_logits_processor.py |
         examples/disaggregated/clients/disagg_client.py |
         examples/disaggregated/slurm/benchmark/submit.py |
         examples/dora/normalize_weights.py |
@@ -1587,7 +1526,6 @@ legacy-files: &legacy_files |
         jenkins/scripts/mergeWaiveList.py |
         jenkins/scripts/open_search_db.py |
         jenkins/scripts/test_rerun.py |
-        scripts/build_cpp_examples.py |
         scripts/build_wheel.py |
         scripts/check_test_list.py |
         scripts/dco_check.py |
@@ -2192,11 +2130,8 @@ legacy-files: &legacy_files |
         tests/integration/defs/conftest.py |
         tests/integration/defs/cpp/conftest.py |
         tests/integration/defs/cpp/cpp_common.py |
-        tests/integration/defs/cpp/test_e2e.py |
         tests/integration/defs/cpp/test_multi_gpu.py |
         tests/integration/defs/cpp/test_unit_tests.py |
-        tests/integration/defs/deterministic/mixtral_deterministic.py |
-        tests/integration/defs/deterministic/test_mixtral_deterministic.py |
         tests/integration/defs/disaggregated/test_auto_scaling.py |
         tests/integration/defs/disaggregated/test_disaggregated.py |
         tests/integration/defs/disaggregated/test_disaggregated_etcd.py |
@@ -2269,7 +2204,6 @@ legacy-files: &legacy_files |
         tests/integration/defs/test_fmha.py |
         tests/integration/defs/test_list_parser.py |
         tests/integration/defs/test_list_validation.py |
-        tests/integration/defs/test_mlpf_results.py |
         tests/integration/defs/test_sanity.py |
         tests/integration/defs/test_unittests.py |
         tests/integration/defs/triton_server/__init__.py |
@@ -2422,7 +2356,6 @@ legacy-files: &legacy_files |
         tests/unittest/_torch/thop/serial/test_moe_alltoall.py |
         tests/unittest/api_stability/api_stability_core.py |
         tests/unittest/api_stability/test_llm_api.py |
-        tests/unittest/bindings/binding_test_utils.py |
         tests/unittest/bindings/test_bindings_moe.py |
         tests/unittest/bindings/test_bindings_ut.py |
         tests/unittest/bindings/test_executor_bindings.py |
@@ -2510,7 +2443,6 @@ legacy-files: &legacy_files |
         tests/unittest/others/test_kv_cache_transceiver.py |
         tests/unittest/others/test_kv_cache_update.py |
         tests/unittest/others/test_layer.py |
-        tests/unittest/others/test_leak.py |
         tests/unittest/others/test_mapping.py |
         tests/unittest/others/test_model_dtype.py |
         tests/unittest/others/test_module.py |

benchmarks/README.md

@@ -1,10 +1,34 @@
-# TensorRT-LLM Benchmarks
+# TensorRT-LLM Benchmarking
 
-## Overview
+For benchmarking TensorRT-LLM, use
+[`trtllm-bench`](../docs/source/developer-guide/perf-benchmarking.md) and
+`trtllm-serve`.
 
-There are currently two workflows to benchmark TensorRT-LLM:
-* [`trtllm-bench`](../docs/source/developer-guide/perf-benchmarking.md)
-  - `trtllm-bench` is native to TensorRT-LLM and is a Python benchmarker for reproducing and testing the performance of TensorRT-LLM.
-  - _NOTE_: This benchmarking suite is a current work in progress and is prone to large changes.
-* [C++ benchmarks](./cpp)
-  - The recommended workflow that uses TensorRT-LLM C++ API and can take advantage of the latest features of TensorRT-LLM.
+This directory keeps the dataset preparation tools consumed by `trtllm-bench`:
+
+- `prepare_dataset.py` — generate benchmark datasets from real data or with
+  synthetic normal/uniform token-length distributions:
+
+  ```bash
+  python3 prepare_dataset.py \
+      --tokenizer <path/to/tokenizer> \
+      --output preprocessed_dataset.json \
+      dataset \
+      --dataset-name <name of the dataset> \
+      --dataset-split <split of the dataset to use> \
+      --dataset-input-key <dataset dictionary key for input> \
+      --dataset-prompt-key <dataset dictionary key for prompt> \
+      --dataset-output-key <dataset dictionary key for output> \
+      [--num-requests 100] \
+      [--max-input-len 1000] \
+      [--output-len-dist 100,10]
+  ```
+
+  Synthetic variants: `python3 prepare_dataset.py ... token-norm-dist ...` and
+  `... token-unif-dist ...`. Run with `--help` for the full option list.
+
+- `utils/prepare_real_data.py`, `utils/prepare_synthetic_data.py` — the
+  subcommand implementations.
+- `utils/generate_rand_loras.py` — generate random LoRA adapters for
+  LoRA benchmarking.
+- `utils/convert_nemo_dataset.py` — convert NeMo chat datasets.