[TRTLLM-14474][chore] Remove legacy python relics and refresh docs after the backend removal#16612
Open
Wanli-Jiang wants to merge 1 commit into
Open
Conversation
…ter the backend removal Trailing python-side cleanup after the legacy TensorRT backend removal (TRTLLM-14026, PR NVIDIA#16369): - Remove legacy quantization-export and plugin-gen relics, the engine-workflow serialization/deprecation shims, and other dead python modules (with their setup.py package_data entries). - Rename tensorrt_llm/bench/build to bench/tuning (build.py -> settings.py, tuning.py -> heuristics.py); the module no longer builds anything. - Remove the top-level benchmarks/ folder entirely. benchmarks/prepare_dataset.py (already marked deprecated upstream) is deduplicated into the packaged tensorrt_llm/bench/dataset implementation behind trtllm-bench prepare-dataset, which gains --tokenizer and --stdout root options as a full replacement; all in-repo callers and docs are repointed. The remaining utils were orphaned legacy-engine helpers (generate_rand_loras.py wrote the removed .npy LoRA engine format; convert_nemo_dataset.py had no consumers). - Fix docs and repo guidance describing the removed backend (customization.md rewrite, AGENTS.md backend table, telemetry doc regeneration). - Prune stale legacy-lint entries (removed files) from legacy-files.txt, the generated ruff configs, and ruff-legacy-baseline.json. Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com>
Wanli-Jiang
marked this pull request as ready for review
July 20, 2026 09:37
Wanli-Jiang
requested review from
brnguyen2,
dc3671,
laikhtewari,
nv-ananjappa,
nv-guomingz,
pcastonguay,
schetlur-nv,
tburt-nv,
tcherckez-nvidia,
tongyuantongyu and
yuanjingx87
July 20, 2026 09:37
BowenFu
approved these changes
Jul 20, 2026
| golden = json.loads((repo_root / _GOLDEN_REL).read_text()) | ||
| content = [_REFERENCE_PREAMBLE] | ||
| for args_class in ("TorchLlmArgs", "TrtLlmArgs"): | ||
| for args_class in ("TorchLlmArgs",): |
| "--output", type=str, help="Output json filename.", default="preprocessed_dataset.json" | ||
| ) | ||
| @click.option( | ||
| "--stdout", |
There was a problem hiding this comment.
Added tokenizer selection and --stdout output options to trtllm-bench prepare-dataset.
Added support for streaming prepared datasets directly to standard output.
Added thinking-budget processing exports for the LLM API.
Should we move the new features to a follow up PR?
Contributor
ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Enterprise Run ID: 📒 Files selected for processing (48)
💤 Files with no reviewable changes (17)
📝 WalkthroughWalkthroughThe change migrates benchmark dataset preparation to ChangesBenchmark modernization
Estimated code review effort: 4 (Complex) | ~60 minutes Sequence Diagram(s)sequenceDiagram
participant User
participant TrtllmBench
participant DatasetWriter
User->>TrtllmBench: invoke prepare-dataset
TrtllmBench->>DatasetWriter: pass dataset generator and stdout flag
DatasetWriter-->>User: stream JSON lines or write output file
Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (3)
tensorrt_llm/bench/dataset/utils.py (2)
105-109: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winAdd type annotations to the modified utility.
Use precise annotations such as
Iterable[str],str | Path, and-> None; also document thatoutput_fileis ignored whenstd_out=True. As per coding guidelines, every Python function must be annotated.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tensorrt_llm/bench/dataset/utils.py` around lines 105 - 109, Update write_dataset_to_file with complete type annotations, using Iterable[str] for dataset_generator, str | Path for output_file, and -> None for the return type. Add documentation stating that output_file is ignored when std_out=True, while preserving the existing stdout behavior.Source: Coding guidelines
105-109: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winCover the new stdout branch with pytest.
Extend
tests/unittest/tools/test_prepare_dataset.pyto verify JSONL emission withstd_out=True, no output-file creation, and the existing file-output path. As per path instructions, keep this QA coverage undertests/unittest/and use pytest.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tensorrt_llm/bench/dataset/utils.py` around lines 105 - 109, Extend the pytest coverage in test_prepare_dataset.py for write_dataset_to_file: verify std_out=True emits the generated items as JSONL to stdout without creating an output file, and retain coverage for the existing file-writing path. Keep the tests under tests/unittest/ and use pytest conventions.Source: Path instructions
tensorrt_llm/bench/tuning/utils.py (1)
27-34: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winAdd the required type annotation and contract documentation.
get_device_memoryis a new public helper without a return annotation or docstring. As per coding guidelines, annotate every function and document external interfaces; usedef get_device_memory() -> floatand describe the GiB result and NVML failure behavior.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tensorrt_llm/bench/tuning/utils.py` around lines 27 - 34, Update get_device_memory with the return annotation -> float and add a docstring documenting that it returns total device memory in GiB and describing the behavior when NVML initialization or queries fail.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@AGENTS.md`:
- Around line 58-64: Update the request-flow architecture text in AGENTS.md to
remove TensorRT from the Executor backend list, leaving only PyTorch and
AutoDeploy. Preserve the surrounding request-flow documentation and backend
table unchanged.
In `@docs/source/commands/trtllm-bench.rst`:
- Around line 23-26: Update the click directive’s :commands: list and opening
subcommand count in the trtllm-bench documentation to include prepare-dataset,
keeping the generated CLI command list consistent with the documented
subcommand.
In `@tensorrt_llm/bench/tuning/utils.py`:
- Around line 27-34: Update get_device_memory so the NVML device lookup and
memory read execute inside a try/finally block, ensuring pynvml.nvmlShutdown()
always runs after a successful pynvml.nvmlInit(), including when either NVML
call raises. Preserve the existing total_memory calculation and return behavior.
---
Nitpick comments:
In `@tensorrt_llm/bench/dataset/utils.py`:
- Around line 105-109: Update write_dataset_to_file with complete type
annotations, using Iterable[str] for dataset_generator, str | Path for
output_file, and -> None for the return type. Add documentation stating that
output_file is ignored when std_out=True, while preserving the existing stdout
behavior.
- Around line 105-109: Extend the pytest coverage in test_prepare_dataset.py for
write_dataset_to_file: verify std_out=True emits the generated items as JSONL to
stdout without creating an output file, and retain coverage for the existing
file-writing path. Keep the tests under tests/unittest/ and use pytest
conventions.
In `@tensorrt_llm/bench/tuning/utils.py`:
- Around line 27-34: Update get_device_memory with the return annotation ->
float and add a docstring documenting that it returns total device memory in GiB
and describing the behavior when NVML initialization or queries fail.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: d8f569d0-f54f-4d53-babd-54c165a61e03
📒 Files selected for processing (48)
.pre-commit-config.yamlAGENTS.mdbenchmarks/README.mdbenchmarks/prepare_dataset.pybenchmarks/utils/__init__.pybenchmarks/utils/convert_nemo_dataset.pybenchmarks/utils/generate_rand_loras.pybenchmarks/utils/prepare_real_data.pybenchmarks/utils/prepare_synthetic_data.pybenchmarks/utils/utils.pydocs/source/_ext/llmapi_config_telemetry.pydocs/source/commands/trtllm-bench.rstdocs/source/developer-guide/perf-overview.mddocs/source/developer-guide/telemetry.mddocs/source/examples/customization.mdexamples/auto_deploy/paragraf/create_standalone_package.pyexamples/layer_wise_benchmarks/sample_performance_alignment.shexamples/quantization/README.mdexamples/quantization/quantize.pylegacy-files.txtpyproject.tomlruff-legacy-baseline.jsonruff-legacy.tomlsetup.pytensorrt_llm/_deprecation.pytensorrt_llm/bench/benchmark/__init__.pytensorrt_llm/bench/benchmark/utils/general.pytensorrt_llm/bench/build/__init__.pytensorrt_llm/bench/dataset/prepare_dataset.pytensorrt_llm/bench/dataset/prepare_real_data.pytensorrt_llm/bench/dataset/prepare_synthetic_data.pytensorrt_llm/bench/dataset/utils.pytensorrt_llm/bench/tuning/__init__.pytensorrt_llm/bench/tuning/dataclasses.pytensorrt_llm/bench/tuning/heuristics.pytensorrt_llm/bench/tuning/settings.pytensorrt_llm/bench/tuning/utils.pytensorrt_llm/llmapi/__init__.pytensorrt_llm/models/convert_utils.pytensorrt_llm/models/unet/pp/__init__.pytensorrt_llm/quantization/__init__.pytensorrt_llm/quantization/image_processing.pytensorrt_llm/quantization/quantize_by_modelopt.pytensorrt_llm/serialization.pytests/unittest/auto_deploy/multigpu/smoke/test_ad_allreduce_strategies.pytests/unittest/auto_deploy/singlegpu/smoke/test_ad_trtllm_bench.pytests/unittest/others/test_quantize_calib_dataset.pytests/unittest/tools/test_prepare_dataset.py
💤 Files with no reviewable changes (17)
- benchmarks/prepare_dataset.py
- benchmarks/README.md
- benchmarks/utils/convert_nemo_dataset.py
- setup.py
- benchmarks/utils/generate_rand_loras.py
- tests/unittest/others/test_quantize_calib_dataset.py
- tensorrt_llm/quantization/image_processing.py
- benchmarks/utils/prepare_synthetic_data.py
- examples/auto_deploy/paragraf/create_standalone_package.py
- examples/quantization/quantize.py
- benchmarks/utils/utils.py
- benchmarks/utils/prepare_real_data.py
- tensorrt_llm/llmapi/init.py
- tensorrt_llm/models/convert_utils.py
- tensorrt_llm/serialization.py
- tensorrt_llm/quantization/quantize_by_modelopt.py
- tensorrt_llm/_deprecation.py
Contributor
There was a problem hiding this comment.
Caution
Inline review comments failed to post. This is likely due to GitHub's internal server error or limits when posting large numbers of comments. If you are seeing this consistently it is likely a permissions issue. Please check "Moderation" -> "Code review limits" under your organization settings.
Actionable comments posted: 3
🧹 Nitpick comments (3)
tensorrt_llm/bench/dataset/utils.py (2)
105-109: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winAdd type annotations to the modified utility.
Use precise annotations such as
Iterable[str],str | Path, and-> None; also document thatoutput_fileis ignored whenstd_out=True. As per coding guidelines, every Python function must be annotated.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tensorrt_llm/bench/dataset/utils.py` around lines 105 - 109, Update write_dataset_to_file with complete type annotations, using Iterable[str] for dataset_generator, str | Path for output_file, and -> None for the return type. Add documentation stating that output_file is ignored when std_out=True, while preserving the existing stdout behavior.Source: Coding guidelines
105-109: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winCover the new stdout branch with pytest.
Extend
tests/unittest/tools/test_prepare_dataset.pyto verify JSONL emission withstd_out=True, no output-file creation, and the existing file-output path. As per path instructions, keep this QA coverage undertests/unittest/and use pytest.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tensorrt_llm/bench/dataset/utils.py` around lines 105 - 109, Extend the pytest coverage in test_prepare_dataset.py for write_dataset_to_file: verify std_out=True emits the generated items as JSONL to stdout without creating an output file, and retain coverage for the existing file-writing path. Keep the tests under tests/unittest/ and use pytest conventions.Source: Path instructions
tensorrt_llm/bench/tuning/utils.py (1)
27-34: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winAdd the required type annotation and contract documentation.
get_device_memoryis a new public helper without a return annotation or docstring. As per coding guidelines, annotate every function and document external interfaces; usedef get_device_memory() -> floatand describe the GiB result and NVML failure behavior.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tensorrt_llm/bench/tuning/utils.py` around lines 27 - 34, Update get_device_memory with the return annotation -> float and add a docstring documenting that it returns total device memory in GiB and describing the behavior when NVML initialization or queries fail.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@AGENTS.md`:
- Around line 58-64: Update the request-flow architecture text in AGENTS.md to
remove TensorRT from the Executor backend list, leaving only PyTorch and
AutoDeploy. Preserve the surrounding request-flow documentation and backend
table unchanged.
In `@docs/source/commands/trtllm-bench.rst`:
- Around line 23-26: Update the click directive’s :commands: list and opening
subcommand count in the trtllm-bench documentation to include prepare-dataset,
keeping the generated CLI command list consistent with the documented
subcommand.
In `@tensorrt_llm/bench/tuning/utils.py`:
- Around line 27-34: Update get_device_memory so the NVML device lookup and
memory read execute inside a try/finally block, ensuring pynvml.nvmlShutdown()
always runs after a successful pynvml.nvmlInit(), including when either NVML
call raises. Preserve the existing total_memory calculation and return behavior.
---
Nitpick comments:
In `@tensorrt_llm/bench/dataset/utils.py`:
- Around line 105-109: Update write_dataset_to_file with complete type
annotations, using Iterable[str] for dataset_generator, str | Path for
output_file, and -> None for the return type. Add documentation stating that
output_file is ignored when std_out=True, while preserving the existing stdout
behavior.
- Around line 105-109: Extend the pytest coverage in test_prepare_dataset.py for
write_dataset_to_file: verify std_out=True emits the generated items as JSONL to
stdout without creating an output file, and retain coverage for the existing
file-writing path. Keep the tests under tests/unittest/ and use pytest
conventions.
In `@tensorrt_llm/bench/tuning/utils.py`:
- Around line 27-34: Update get_device_memory with the return annotation ->
float and add a docstring documenting that it returns total device memory in GiB
and describing the behavior when NVML initialization or queries fail.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: d8f569d0-f54f-4d53-babd-54c165a61e03
📒 Files selected for processing (48)
.pre-commit-config.yamlAGENTS.mdbenchmarks/README.mdbenchmarks/prepare_dataset.pybenchmarks/utils/__init__.pybenchmarks/utils/convert_nemo_dataset.pybenchmarks/utils/generate_rand_loras.pybenchmarks/utils/prepare_real_data.pybenchmarks/utils/prepare_synthetic_data.pybenchmarks/utils/utils.pydocs/source/_ext/llmapi_config_telemetry.pydocs/source/commands/trtllm-bench.rstdocs/source/developer-guide/perf-overview.mddocs/source/developer-guide/telemetry.mddocs/source/examples/customization.mdexamples/auto_deploy/paragraf/create_standalone_package.pyexamples/layer_wise_benchmarks/sample_performance_alignment.shexamples/quantization/README.mdexamples/quantization/quantize.pylegacy-files.txtpyproject.tomlruff-legacy-baseline.jsonruff-legacy.tomlsetup.pytensorrt_llm/_deprecation.pytensorrt_llm/bench/benchmark/__init__.pytensorrt_llm/bench/benchmark/utils/general.pytensorrt_llm/bench/build/__init__.pytensorrt_llm/bench/dataset/prepare_dataset.pytensorrt_llm/bench/dataset/prepare_real_data.pytensorrt_llm/bench/dataset/prepare_synthetic_data.pytensorrt_llm/bench/dataset/utils.pytensorrt_llm/bench/tuning/__init__.pytensorrt_llm/bench/tuning/dataclasses.pytensorrt_llm/bench/tuning/heuristics.pytensorrt_llm/bench/tuning/settings.pytensorrt_llm/bench/tuning/utils.pytensorrt_llm/llmapi/__init__.pytensorrt_llm/models/convert_utils.pytensorrt_llm/models/unet/pp/__init__.pytensorrt_llm/quantization/__init__.pytensorrt_llm/quantization/image_processing.pytensorrt_llm/quantization/quantize_by_modelopt.pytensorrt_llm/serialization.pytests/unittest/auto_deploy/multigpu/smoke/test_ad_allreduce_strategies.pytests/unittest/auto_deploy/singlegpu/smoke/test_ad_trtllm_bench.pytests/unittest/others/test_quantize_calib_dataset.pytests/unittest/tools/test_prepare_dataset.py
💤 Files with no reviewable changes (17)
- benchmarks/prepare_dataset.py
- benchmarks/README.md
- benchmarks/utils/convert_nemo_dataset.py
- setup.py
- benchmarks/utils/generate_rand_loras.py
- tests/unittest/others/test_quantize_calib_dataset.py
- tensorrt_llm/quantization/image_processing.py
- benchmarks/utils/prepare_synthetic_data.py
- examples/auto_deploy/paragraf/create_standalone_package.py
- examples/quantization/quantize.py
- benchmarks/utils/utils.py
- benchmarks/utils/prepare_real_data.py
- tensorrt_llm/llmapi/init.py
- tensorrt_llm/models/convert_utils.py
- tensorrt_llm/serialization.py
- tensorrt_llm/quantization/quantize_by_modelopt.py
- tensorrt_llm/_deprecation.py
🛑 Comments failed to post (3)
AGENTS.md (1)
58-64: 📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
Remove the stale TensorRT backend from the request-flow documentation.
The new backend table says only PyTorch and AutoDeploy remain, but Line 70 still says
Executor (PyTorch/AutoDeploy/TensorRT). Change it toExecutor (PyTorch/AutoDeploy)so the architecture guidance is consistent.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@AGENTS.md` around lines 58 - 64, Update the request-flow architecture text in AGENTS.md to remove TensorRT from the Executor backend list, leaving only PyTorch and AutoDeploy. Preserve the surrounding request-flow documentation and backend table unchanged.docs/source/commands/trtllm-bench.rst (1)
23-26: 📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
Include
prepare-datasetin the generated command list.The click directive at Line 16 still lists only
throughput, latency, build, so the new command is absent from generated CLI syntax. Update:commands:and the opening subcommand count to includeprepare-dataset.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@docs/source/commands/trtllm-bench.rst` around lines 23 - 26, Update the click directive’s :commands: list and opening subcommand count in the trtllm-bench documentation to include prepare-dataset, keeping the generated CLI command list consistent with the documented subcommand.tensorrt_llm/bench/tuning/utils.py (1)
27-34: 🩺 Stability & Availability | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash set -euo pipefail git ls-files tensorrt_llm/bench/tuning/utils.py wc -l tensorrt_llm/bench/tuning/utils.py cat -n tensorrt_llm/bench/tuning/utils.py | sed -n '1,120p' rg -n "get_device_memory|nvmlInit|nvmlShutdown|pynvml" tensorrt_llm/bench -SRepository: NVIDIA/TensorRT-LLM
Length of output: 3132
🏁 Script executed:
#!/bin/bash set -euo pipefail sed -n '280,330p' tensorrt_llm/bench/dataclasses/reporting.py sed -n '1,140p' tensorrt_llm/bench/tuning/heuristics.py python3 - <<'PY' from pathlib import Path text = Path("tensorrt_llm/bench/tuning/utils.py").read_text() print("try/finally present:", "try:" in text and "finally:" in text) print("nvmlShutdown count:", text.count("nvmlShutdown")) PYRepository: NVIDIA/TensorRT-LLM
Length of output: 8583
Guard NVML teardown in
get_device_memory()
IfnvmlDeviceGetHandleByIndex()ornvmlDeviceGetMemoryInfo()raises afternvmlInit(),nvmlShutdown()is skipped and NVML stays initialized. Wrap the lookup/read intry/finally.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tensorrt_llm/bench/tuning/utils.py` around lines 27 - 34, Update get_device_memory so the NVML device lookup and memory read execute inside a try/finally block, ensuring pynvml.nvmlShutdown() always runs after a successful pynvml.nvmlInit(), including when either NVML call raises. Preserve the existing total_memory calculation and return behavior.
mikeiovine
requested review from
mikeiovine
and removed request for
pcastonguay and
schetlur-nv
July 20, 2026 15:24
mikeiovine
approved these changes
Jul 20, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why this PR exists
Phase C removed the TensorRT engine backend. This PR removes the python
modules, packaging entries, and lint bookkeeping that existed only to
serve it, deduplicates the benchmark dataset tooling, and fixes docs that
still described the removed workflow. It is independent of the other
Phase D PRs (infra / tests-examples / cpp-cleanup): all are based
directly on main and merge cleanly in any order.
Change groups
1. Legacy quantization-export and plugin-gen relics
tensorrt_llm/quantization/quantize_by_modelopt.py(1,332 lines)trtllm-build; the PyTorch backend quantizes via ModelOpt directlytensorrt_llm/quantization/image_processing.pyexamples/quantization/quantize.py+tests/unittest/others/test_quantize_calib_dataset.pytensorrt_llm/_deprecation.pytensorrt_llm/models/unet/pp/__init__.pysetup.pyentriespackage_dataglobs fortools/plugin_gen/templates/*andbench/build/benchmark_config.yml— both paths no longer exist after this PRserialization.pywhitelist entry"tensorrt_llm.builder": ["BuildConfig"]— the module it whitelists is gonePlus the import/
__init__.pyfan-out intensorrt_llm/quantization/,llmapi/,models/convert_utils.py, and_utils.py.2.
tensorrt_llm/bench/build→bench/tuningrenameThe module stopped building engines long ago; it only computes tuning
heuristics for
trtllm-bench. Renamed to say what it is:build.py → settings.py,tuning.py → heuristics.py,dataclasses.py/utils.pycarried over; importers inbench/benchmark/repointed. No public API surface — nothing outsidetensorrt_llm.benchimports these modules.3. Benchmark dataset tooling deduplicated;
benchmarks/folder removedbenchmarks/prepare_dataset.py(already@click.group(deprecated=True)upstream) and its
utils/had forked from the packaged copy. Thepackaged
tensorrt_llm/bench/dataset/implementation behindtrtllm-bench prepare-datasetis now the single entry point, gaining:--tokenizerroot option (falls back totrtllm-bench --model;UsageErrorif neither) — full CLI parity with the old standalone;--stdoutflag (JSON entry per line) preserving pipe workflows.sample_performance_alignment.sh,tests/unittest/tools/test_prepare_dataset.py).benchmarks/utils/files were orphaned legacy-enginehelpers:
generate_rand_loras.pywrote the removed.npyLoRA engineformat;
convert_nemo_dataset.pyhad no consumers.perf-overview.md,trtllm-bench.rst) usetrtllm-bench --model <m> prepare-dataset --output <file> ...(file mode deliberately: the
import tensorrt_llmversion banner is abare
print()to stdout, so--stdout > filepiping would prepend thebanner — a possible separate
[None][infra]fix is moving that bannerto stderr).
later, retrievable from git history): local-directory dataset loading
and the multimodal image dump from the standalone copy.
4. Docs / repo guidance refresh
docs/source/examples/customization.mdrewritten — it imported theremoved
BuildConfigand documented engine building end-to-end.AGENTS.mdbackend table: TensorRT row marked removed.docs/source/_ext/llmapi_config_telemetry.pyno longer iteratesTrtLlmArgs;telemetry.mdregenerated (−298 lines).5. Legacy-lint bookkeeping (~2,800 lines of generated-config churn)
All Phase D lint pruning rides in this PR to keep it out of the other
three: 528 stale
legacy-files.txtentries for removed files, theregenerated
ruff-legacy.toml/pyproject.toml/.pre-commit-config.yamlmanaged blocks, and 184 stale
ruff-legacy-baseline.jsonkeys with_metatotals updated in the same change.legacy_utils.py check-configspasses.
Note: files deleted by the tests-examples PR (TRTLLM-14473) leave a small
number of newly-stale entries — a mechanical
prune-files+gen-configsfollow-up runs once after both PRs merge (kept out of both to avoid
cross-PR conflicts).
Reviewer callouts
ParallelConfig/executor surface is untouched here — C++-sideremovals are in the cpp-cleanup PR (TRTLLM-14475).
tests/unittest/api_stabilitysurface is touched;the deleted modules were not part of the committed LLM API.
trtllm-bench prepare-dataset --tokenizeris a small additive CLIchange to a bench subcommand (bench-owner ack).
Validation
python3 -c "import tensorrt_llm"and the attention/bench importfan-out verified after each rename/deletion.
--tokenizerstandalone (no benchcontext),
--stdout(clean JSON lines), file mode, and thetrtllm-bench --modelfallback path all pass.scripts/legacy_utils.py check-configspasses; full pre-commit passes.origin/mainisconflict-free (the only shared file,
setup.py, is touched in disjointhunks by the infra PR).
Summary by CodeRabbit
New Features
--stdoutoutput options totrtllm-bench prepare-dataset.Changes
trtllm-bench prepare-dataset.Documentation
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)
If PR introduces API changes, an appropriate PR label is added - either
api-compatibleorapi-breaking. Forapi-breaking, includeBREAKINGin the PR title.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
To see a list of available CI bot commands, please comment
/bot help.