Software health reportschema 0.27.0 · metrics 2.5.0 · 2026-07-30 14:48 UTC

pytorch / TensorRT

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

Python · Jupyter Notebook · C++BSD-3-Clause★ 2,984 stars⑂ 410 forkssince Mar 2020View on GitHub ↗

#tensorrt #libtorch #machine-learning #pytorch #deep-learning #jetson #nvidia #cuda

pytorch/TensorRT holds a health index of 92 out of 100, placing it in the Excellent band. It scores highest on Vitality (96/100) and lowest on Security (21/100). It was last updated today. 2 contributors account for most of its recent work.

overall / 100

Excellent

Software health index

Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.

Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met

Excellent80-92Strong across the board; minor gaps

Good65-79Healthy; gaps are limited and manageable

Moderate50-64Acceptable with notable gaps; review recommended

Weak35-49Material weaknesses across several areas

At Risk20-34Significant weaknesses; adoption warrants caution

Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)

Score profile

Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.

The weighted overall 78 is calibrated to 92 on the published index scale (record calibration 2026-08-02).

Ownership

pytorchOrganization

13,436 followers70 public repossince Aug 2016

This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.

Package ecosystems

Registry	Package	Version	Downloads / mo	Versions	Last publish	Tags
PyPI	torch-tensorrt-rtx	2.13.0	-	5	1 day ago	pytorch torch tensorrt trt ai artificial-intelligence ml machine-learning dl deep-learning compiler dynamo torchscript inference
PyPI	torch_tensorrt	2.13.0	-	18	1 day ago	pytorch torch tensorrt trt ai artificial-intelligence ml machine-learning dl deep-learning compiler dynamo torchscript inference

Metrics by category

Vitality

Is the project alive — is code being written and are releases shipping?

96Exceptional · 21% of overall

Development activity

98Exceptional

How it's scored

36/36	Push recency — last push 0 days ago
34.6/36	Commit cadence — 50/52 weeks with commits
18/18	Commit volume — 530 commits in the last year
0/10	OpenSSF Scorecard: Maintained — no data

Inputs used

commits_last_year	530
human_commit_share	0.99
days_since_last_push	0
active_weeks_last_year	50

Release discipline

92Excellent

How it's scored

27/27	Ships releases — 28 releases published
36/36	Release recency — latest release 1 days ago
19.8/27	Release cadence — a release every ~59.8 days
0/10	OpenSSF Scorecard: Signed-Releases — no data

Inputs used

releases_count	28
latest_release_tag	v2.13.0
releases_from_tags	no
days_since_latest_release	1
mean_days_between_releases	59.8

Community & Adoption

Does the project have users, downloads, attention, and a welcoming setup for contributors?

90Excellent · 17% of overall

Popularity & adoption

88Excellent

How it's scored

56.4/60	Stars — 2,984 stars
21.8/25	Forks — 410 forks
10.1/15	Watchers — 66 watchers

Inputs used

forks	410
stars	2,984
watchers	66
growth_state	unverified
growth_factor_pct	100
growth_unverified_reason	no_history

Community health

92Excellent

How it's scored

22.5/22.5	README
22.5/22.5	License — recognized license (BSD-3-Clause)
18/18	CONTRIBUTING guide
13.5/13.5	Code of conduct
0/7.2	Issue template
6.3/6.3	PR template

Inputs used

has_readme	yes
has_license	yes
readme_badges	—
has_contributing	yes
has_issue_template	no
has_code_of_conduct	yes
readme_badge_services	—
has_pull_request_template	yes

Sustainability & Governance

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?

78Good · 23% of overall

Maintainer resilience (bus factor)

58Moderate

How it's scored

25.2/54	Bus factor — 2 contributor(s) cover half of all commits
13.5/22.5	Commit distribution — top contributor authored 40% of commits
13.5/13.5	Contributor breadth — 99 contributors
0/10	OpenSSF Scorecard: Contributors — no data

Inputs used

bus_factor	2
contributors_sampled	99
top_contributor_share	0.401

Issue & PR responsiveness

82Excellent

How it's scored

34.9/42	Issue resolution — 83% of issues closed
24.3/30	PR acceptance — 1,900/2,348 decided PRs merged
0/13	Newcomer PR acceptance — no first-time contributor's PR decided in 30d
0/15	OpenSSF Scorecard: Code-Review — no data

Inputs used

merged_prs	1,900
open_issues	317
closed_issues	1,566
prs_merged_7d	—
prs_decided_7d	—
prs_merged_30d	—
prs_decided_30d	—
issue_closed_ratio	0.832
closed_unmerged_prs	448
first_time_authors_30d	—
first_time_prs_merged_30d	—
first_time_prs_decided_30d	—

Excluded from scoring (no data or not applicable): newcomer_pr_acceptance. Remaining weights renormalized.

Ownership & stewardship

80Excellent

How it's scored

30/30	Ownership backing — organization-owned
0/20	Verified domain
25/25	Owner reach — 13,436 followers of pytorch
25/25	Track record — 70 public repos, account ~9 yr old

Inputs used

followers	13,436
owner_type	Organization
is_verified	—
owner_login	pytorch
public_repos	70
account_age_days	3,638

Package maintenance

100Exceptional

How it's scored

25/25	Published & resolvable — 2 package(s) on pypi
35/35	Publish recency — latest publish 1 days ago
20/20	Version history — 18 published versions
20/20	Not deprecated — active, not deprecated or yanked

Inputs used

packages	torch-tensorrt-rtx, torch_tensorrt
ecosystems	pypi
any_deprecated	no
min_days_since_publish	1

Engineering Quality

Are baseline engineering and documentation practices in place?

95Exceptional · 19% of overall

Engineering practices

92Excellent

How it's scored

24/24	CI workflows — 36 workflow(s)
24/24	Tests present
16/16	Linter config
9.6/9.6	Pre-commit hooks
0/6.4	.editorconfig
0/20	OpenSSF Scorecard: CI-Tests — no data

Inputs used

has_ci	yes
has_tests	yes
has_editorconfig	no
has_linter_config	yes
has_precommit_config	yes

Documentation

100Exceptional

How it's scored

30/30	README
25/25	Documentation directory
15/15	Documentation / homepage site — https://pytorch.org/TensorRT
10/10	Repository description
10/10	Topics — 8 topics
10/10	Wiki

Inputs used

topics	tensorrt, libtorch, machine-learning, pytorch, deep-learning, jetson, nvidia, cuda
has_wiki	yes
homepage	https://pytorch.org/TensorRT
has_readme	yes
has_docs_dir	yes
has_description	yes

Security

Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?

21At Risk · 16% of overall

Security posture

1Critical

How it's scored

0/30	Security policy (SECURITY.md)
0/25	Dependabot config
0/25	Dependency lockfiles — published library — lockfiles are an application concern, not expected
0/20	CodeQL workflow

Inputs used

source	file_signals
lockfiles	package-lock.json, uv.lock
manifests	docsrc/requirements.txt, py/requirements.txt, pyproject.toml, requirements-dev.txt, setup.py
has_codeql_workflow	no
has_security_policy	no
has_dependabot_config	no

Excluded from scoring (no data or not applicable): Dependency lockfiles. Remaining weights renormalized.

Dependency advisories

100Exceptional

How it's scored

35/35	Direct dependencies free of known advisories — no direct dependency carries a known advisory
25/25	Indirect dependencies free of known advisories — no indirect dependency carries a known advisory
0/40	No advisories left outstanding — no advisory carries a publication date

Inputs used

source	osv
advisories	0
affected_packages	0
assessed_packages	11
unassessed_packages	0
affected_by_severity	none
direct_affected_packages	0

Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the pypi:torch-tensorrt-rtx@2.13.0 runtime dependency closure — what installing the published package pulls in — 11 packages. Reachability is not analyzed.

AI Readiness

How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.

68Good · 4% of overall

Agent context & guidance

40Weak

How it's scored

0/45	Agent instructions — no CLAUDE.md / AGENTS.md / editor rules
0/15	Machine-readable docs (llms.txt)
40/40	Legible commit history — 95 of 99 human commits state their intent (structured subject or explanatory body)

Inputs used

has_llms_txt	no
legible_history_share	0.96
agent_instruction_files	—
agent_instruction_max_bytes	—

Verify loop (build / test / typecheck)

96Exceptional

How it's scored

18/18	One-command bootstrap — docsrc/Makefile, examples/int8/ptq/Makefile, examples/int8/qat/Makefile, examples/torchtrt_aoti_example/Makefile, examples/torchtrt_runtime_example/Makefile, justfile, noxfile.py
22/22	Automated tests
11/11	Lint / format config
11/11	Static type checking — .github/actions/assigner/tsconfig.json
10/10	Reproducible environment — Dockerfile, lockfile
6/10	Demonstrated agent practice — 3 of the last 100 commits agent-authored or agent-credited
8/8	Automated maintenance — 1 of the last 100 commits are automated dependency updates
0/10	OpenSSF Scorecard: Pinned-Dependencies — no data

Inputs used

has_nix	no
has_tests	yes
lockfiles	package-lock.json, uv.lock
has_dockerfile	yes
typed_language	no
bootstrap_files	docsrc/Makefile, examples/int8/ptq/Makefile, examples/int8/qat/Makefile, examples/torchtrt_aoti_example/Makefile, examples/torchtrt_runtime_example/Makefile, justfile, noxfile.py
has_devcontainer	no
has_linter_config	yes
typecheck_configs	.github/actions/assigner/tsconfig.json
agent_commit_share	0.03
toolchain_manifests	—
dependency_bot_commit_share	0.01

Code legibility for models

77Good

How it's scored

27/45	Type-checkable code — Python with type-check config (.github/actions/assigner/tsconfig.json)
49.7/55	Manageable file sizes — 386/4,006 source files over 60KB

Inputs used

primary_language	Python
largest_source_bytes	555,307
source_files_sampled	4,006
oversized_source_files	386

Machine-readable interfaces

40Weak

How it's scored

0/40	API schema (OpenAPI/GraphQL/proto)
0/20	MCP server
40/40	Runnable examples — examples, notebooks

Inputs used

example_dirs	examples, notebooks
has_mcp_signal	no
api_schema_files	—

Key facts

2,984GitHub stars

99contributors

530commits, last 12 months

0days since last push

28releases

2bus factor

317open issues

PyPIpackage ecosystems

Data collection warnings

Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
OpenSSF Scorecard did not return a usable result (2026/07/30 14:46:54 Warning: PATs stored in env variables GITHUB_AUTH_TOKEN and GITHUB_TOKEN differ. Scorecard will use the former.); skipping Scorecard checks

More detail

Star and fork history 0 ★ / 410 ⇿

0Stars

410Forks

27Releases

When each star and fork was added, collected from GitHub and bucketed by day. Cumulative growth sits directly above the daily additions it is made of, so the two read against each other: steady organic accretion looks nothing like an abrupt, short-lived burst. Where that difference is measurable, it is reported as growth authenticity.

Major 1Minor 19Patch 7

Each point covers 6 days.

All dependencies 295

Full resolved dependency set from the GitHub dependency graph: 0 direct and 295 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

Registry	Package	Version	Relation
npm	@actions/core	`1.9.1`	indirect
npm	@actions/github	`6.0.0`	indirect
npm	@actions/http-client	`2.2.3`	indirect
npm	@fastify/busboy	`2.1.1`	indirect
npm	@octokit/auth-token	`4.0.0`	indirect
npm	@octokit/core	`5.2.0`	indirect
npm	@octokit/endpoint	`9.0.6`	indirect
npm	@octokit/graphql	`7.1.0`	indirect
npm	@octokit/openapi-types	`20.0.0`	indirect
npm	@octokit/openapi-types	`23.0.1`	indirect
npm	@octokit/plugin-paginate-rest	`9.2.2`	indirect
npm	@octokit/plugin-rest-endpoint-methods	`10.4.1`	indirect
npm	@octokit/request	`8.4.1`	indirect
npm	@octokit/request-error	`5.1.1`	indirect
npm	@octokit/types	`12.6.0`	indirect
npm	@octokit/types	`13.8.0`	indirect
npm	@types/node	`17.0.35`	indirect
npm	@vercel/ncc	`0.33.4`	indirect
npm	argparse	`2.0.1`	indirect
npm	before-after-hook	`2.2.3`	indirect
npm	deprecation	`2.3.1`	indirect
npm	fs	`0.0.1-security`	indirect
npm	js-yaml	`4.1.1`	indirect
npm	once	`1.4.0`	indirect
npm	prettier	`2.6.2`	indirect
npm	tunnel	`0.0.6`	indirect
npm	typescript	`4.6.4`	indirect
npm	undici	`5.29.0`	indirect
npm	universal-user-agent	`6.0.1`	indirect
npm	uuid	`8.3.2`	indirect
npm	wrappy	`1.0.2`	indirect
PyPI	accelerate	`1.13.0`	indirect
PyPI	accessible-pygments	`0.0.5`	indirect
PyPI	aiohappyeyeballs	`2.6.1`	indirect
PyPI	aiohttp	`3.13.5`	indirect
PyPI	aiosignal	`1.4.0`	indirect
PyPI	alabaster	`0.7.16`	indirect
PyPI	annotated-doc	`0.0.4`	indirect
PyPI	annotated-types	`0.7.0`	indirect
PyPI	anyio	`4.13.0`	indirect
PyPI	apache-tvm-ffi	`0.1.10`	indirect
PyPI	argparse	`—`	indirect
PyPI	async-timeout	`5.0.1`	indirect
PyPI	attrs	`26.1.0`	indirect
PyPI	babel	`2.18.0`	indirect
PyPI	backports-strenum	`1.3.1`	indirect
PyPI	beautifulsoup4	`4.14.3`	indirect
PyPI	black	`—`	indirect
PyPI	black	`26.3.1`	indirect
PyPI	bleach	`6.3.0`	indirect
PyPI	breathe	`4.36.0`	indirect
PyPI	cattrs	`26.1.0`	indirect
PyPI	certifi	`2026.2.25`	indirect
PyPI	cffi	`2.0.0`	indirect
PyPI	cfgv	`3.5.0`	indirect
PyPI	charset-normalizer	`3.4.7`	indirect
PyPI	clang-format	`14.0.6`	indirect
PyPI	click	`8.3.2`	indirect
PyPI	colorama	`0.4.6`	indirect
PyPI	coremltools	`9.0`	indirect
PyPI	cuda-bindings	`13.2.0`	indirect
PyPI	cuda-core	`1.0.1`	indirect
PyPI	cuda-pathfinder	`1.5.3`	indirect
PyPI	cuda-python	`13.2.0`	indirect
PyPI	cuda-tile	`1.3.0`	indirect
PyPI	cuda-toolkit	`13.0.3.0`	indirect
PyPI	cupy	`13.1.0`	indirect
PyPI	datasets	`5.0.0`	indirect
PyPI	deepspeed	`0.18.9`	indirect
PyPI	defusedxml	`0.7.1`	indirect
PyPI	diffusers	`0.30.3`	indirect
PyPI	diffusers	`0.34.0`	indirect
PyPI	diffusers	`0.37.1`	indirect
PyPI	dill	`0.4.1`	indirect
PyPI	distlib	`0.4.0`	indirect
PyPI	dllist	`—`	indirect
PyPI	dllist	`2.0.0`	indirect
PyPI	docutils	`0.20`	indirect
PyPI	einops	`0.8.2`	indirect
PyPI	exceptiongroup	`1.3.1`	indirect
PyPI	execnet	`2.1.2`	indirect
PyPI	executorch	`1.3.1`	indirect
PyPI	exhale	`0.3.7`	indirect
PyPI	expecttest	`—`	indirect
PyPI	expecttest	`0.1.6`	indirect
PyPI	fastjsonschema	`2.21.2`	indirect
PyPI	filelock	`—`	indirect
PyPI	filelock	`3.29.0`	indirect
PyPI	flashinfer-python	`0.3.1.post1`	indirect
PyPI	flashinfer-python	`0.6.8.post1`	indirect
PyPI	flatbuffers	`25.12.19`	indirect
PyPI	frozenlist	`1.8.0`	indirect
PyPI	fsspec	`2026.3.0`	indirect
PyPI	graphviz	`0.21`	indirect
PyPI	h11	`0.16.0`	indirect
PyPI	hf-xet	`1.4.3`	indirect
PyPI	hjson	`3.1.0`	indirect
PyPI	httpcore	`1.0.9`	indirect
PyPI	httpx	`0.28.1`	indirect
PyPI	huggingface-hub	`—`	indirect
PyPI	huggingface-hub	`1.11.0`	indirect
PyPI	hydra-core	`1.4.0.dev1`	indirect
PyPI	hypothesis	`6.155.1`	indirect
PyPI	identify	`2.6.19`	indirect
PyPI	idna	`3.11`	indirect
PyPI	imagesize	`2.0.0`	indirect
PyPI	importlib-metadata	`9.0.0`	indirect
PyPI	iniconfig	`2.3.0`	indirect
PyPI	isort	`—`	indirect
PyPI	isort	`8.0.1`	indirect
PyPI	jinja2	`3.1.6`	indirect
PyPI	joblib	`1.5.3`	indirect
PyPI	jsonschema	`4.26.0`	indirect
PyPI	jsonschema-specifications	`2025.9.1`	indirect
PyPI	jupyter-client	`8.8.0`	indirect
PyPI	jupyter-core	`5.9.1`	indirect
PyPI	jupyterlab-pygments	`0.3.0`	indirect
PyPI	kgb	`7.3`	indirect
PyPI	librt	`0.9.0`	indirect
PyPI	lxml	`6.1.0`	indirect
PyPI	markdown-it-py	`4.0.0`	indirect
PyPI	markupsafe	`3.0.2`	indirect
PyPI	markupsafe	`3.0.3`	indirect
PyPI	matplotlib	`—`	indirect
PyPI	mdurl	`0.1.2`	indirect
PyPI	mistune	`3.2.0`	indirect
PyPI	monai	`1.5.2rc1`	indirect
PyPI	mpmath	`1.3.0`	indirect
PyPI	msgpack	`1.1.2`	indirect
PyPI	multidict	`6.7.1`	indirect
PyPI	multiprocess	`0.70.19`	indirect
PyPI	mypy	`—`	indirect
PyPI	mypy	`1.20.1`	indirect
PyPI	mypy-extensions	`1.1.0`	indirect
PyPI	nbclient	`0.10.4`	indirect
PyPI	nbconvert	`7.17.1`	indirect
PyPI	nbformat	`5.10.4`	indirect
PyPI	nbsphinx	`0.9.3`	indirect
PyPI	networkx	`—`	indirect
PyPI	networkx	`2.8.8`	indirect
PyPI	networkx	`3.4.2`	indirect
PyPI	networkx	`3.6.1`	indirect
PyPI	ninja	`1.13.0`	indirect
PyPI	nltk	`3.9.4`	indirect
PyPI	nodeenv	`1.10.0`	indirect
PyPI	numpy	`—`	indirect
PyPI	numpy	`2.2.6`	indirect
PyPI	numpy	`2.4.4`	indirect
PyPI	nvidia-cublas	`13.1.1.3`	indirect
PyPI	nvidia-cuda-cupti	`13.0.85`	indirect
PyPI	nvidia-cuda-nvrtc	`13.0.88`	indirect
PyPI	nvidia-cuda-runtime	`13.0.96`	indirect
PyPI	nvidia-cudnn-cu13	`9.23.1.3`	indirect
PyPI	nvidia-cudnn-frontend	`1.22.1`	indirect
PyPI	nvidia-cufft	`12.0.0.61`	indirect
PyPI	nvidia-cufile	`1.15.1.6`	indirect
PyPI	nvidia-curand	`10.4.0.35`	indirect
PyPI	nvidia-cusolver	`12.0.4.66`	indirect
PyPI	nvidia-cusparse	`12.6.3.3`	indirect
PyPI	nvidia-cusparselt-cu13	`0.8.1`	indirect
PyPI	nvidia-cutlass-dsl	`4.4.2`	indirect
PyPI	nvidia-cutlass-dsl-libs-base	`4.4.2`	indirect
PyPI	nvidia-ml-py	`13.595.45`	indirect
PyPI	nvidia-modelopt	`—`	indirect
PyPI	nvidia-modelopt	`0.45.0`	indirect
PyPI	nvidia-nccl-cu13	`2.30.7`	indirect
PyPI	nvidia-nvjitlink	`13.0.88`	indirect
PyPI	nvidia-nvshmem-cu13	`3.4.5`	indirect
PyPI	nvidia-nvtx	`13.0.85`	indirect
PyPI	nvidia-pyindex	`—`	indirect
PyPI	omegaconf	`2.4.0.dev10`	indirect
PyPI	onnx	`—`	indirect
PyPI	opencv-python	`—`	indirect
PyPI	packaging	`—`	indirect
PyPI	packaging	`26.1`	indirect
PyPI	pandas	`—`	indirect
PyPI	pandas	`2.3.3`	indirect
PyPI	pandas	`3.0.2`	indirect
PyPI	pandocfilters	`1.5.1`	indirect
PyPI	parameterized	`—`	indirect
PyPI	parameterized	`0.9.0`	indirect
PyPI	pathspec	`1.0.4`	indirect
PyPI	peft	`0.19.1`	indirect
PyPI	pillow	`—`	indirect
PyPI	pillow	`12.2.0`	indirect
PyPI	platformdirs	`4.9.6`	indirect
PyPI	pluggy	`1.6.0`	indirect
PyPI	pre-commit	`—`	indirect
PyPI	pre-commit	`4.5.1`	indirect
PyPI	propcache	`0.4.1`	indirect
PyPI	protobuf	`3.20.*`	indirect
PyPI	protobuf	`7.35.0`	indirect
PyPI	psutil	`7.2.2`	indirect
PyPI	pulp	`3.3.0`	indirect
PyPI	py	`1.11.0`	indirect
PyPI	py-cpuinfo	`9.0.0`	indirect
PyPI	pyaml	`26.2.1`	indirect
PyPI	pyarrow	`23.0.1`	indirect
PyPI	pybind11	`2.6.2`	indirect
PyPI	pycparser	`3.0`	indirect
PyPI	pydantic	`2.13.3`	indirect
PyPI	pydantic-core	`2.46.3`	indirect
PyPI	pydata-sphinx-theme	`0.15.4`	indirect
PyPI	pydot	`4.0.1`	indirect
PyPI	pygithub	`—`	indirect
PyPI	pygments	`2.20.0`	indirect
PyPI	pynvml	`13.0.1`	indirect
PyPI	pyparsing	`3.3.2`	indirect
PyPI	pytest	`—`	indirect
PyPI	pytest	`9.1.1`	indirect
PyPI	pytest-forked	`1.6.0`	indirect
PyPI	pytest-github-actions-annotate-failures	`0.4.2`	indirect
PyPI	pytest-rerunfailures	`16.4`	indirect
PyPI	pytest-xdist	`—`	indirect
PyPI	pytest-xdist	`3.8.0`	indirect
PyPI	python-dateutil	`2.9.0.post0`	indirect
PyPI	python-discovery	`1.2.2`	indirect
PyPI	pytokens	`0.4.1`	indirect
PyPI	pytorch-sphinx-theme2	`0.4.4`	indirect
PyPI	pytorch-tokenizers	`1.3.0`	indirect
PyPI	pytz	`2026.1.post1`	indirect
PyPI	pyyaml	`—`	indirect
PyPI	pyyaml	`6.0.3`	indirect
PyPI	pyzmq	`27.1.0`	indirect
PyPI	referencing	`0.37.0`	indirect
PyPI	regex	`2026.4.4`	indirect
PyPI	requests	`2.33.1`	indirect
PyPI	rich	`15.0.0`	indirect
PyPI	rpds-py	`0.30.0`	indirect
PyPI	ruamel-yaml	`0.19.1`	indirect
PyPI	ruff	`—`	indirect
PyPI	ruff	`0.15.11`	indirect
PyPI	safetensors	`0.7.0`	indirect
PyPI	scikit-learn	`1.7.1`	indirect
PyPI	scipy	`1.15.3`	indirect
PyPI	scipy	`1.17.1`	indirect
PyPI	sentencepiece	`0.2.1`	indirect
PyPI	setuptools	`—`	indirect
PyPI	setuptools	`78.1.1`	indirect
PyPI	setuptools	`81.0.0`	indirect
PyPI	shellingham	`1.5.4`	indirect
PyPI	six	`1.17.0`	indirect
PyPI	snowballstemmer	`3.0.1`	indirect
PyPI	sortedcontainers	`2.4.0`	indirect
PyPI	soupsieve	`2.8.3`	indirect
PyPI	sphinx	`7.2.6`	indirect
PyPI	sphinx-gallery	`0.13.0`	indirect
PyPI	sphinxcontrib-applehelp	`2.0.0`	indirect
PyPI	sphinxcontrib-devhelp	`2.0.0`	indirect
PyPI	sphinxcontrib-htmlhelp	`2.1.0`	indirect
PyPI	sphinxcontrib-jsmath	`1.0.1`	indirect
PyPI	sphinxcontrib-qthelp	`2.0.0`	indirect
PyPI	sphinxcontrib-serializinghtml	`2.0.0`	indirect
PyPI	sympy	`1.14.0`	indirect
PyPI	tabulate	`0.10.0`	indirect
PyPI	tensorboard	`—`	indirect
PyPI	tensorrt	`11.1.0.106`	indirect
PyPI	tensorrt-cu13	`11.1.0.106`	indirect
PyPI	tensorrt-cu13-bindings	`11.1.0.106`	indirect
PyPI	tensorrt-cu13-libs	`11.1.0.106`	indirect
PyPI	threadpoolctl	`3.6.0`	indirect
PyPI	tiktoken	`0.13.0`	indirect
PyPI	timm	`—`	indirect
PyPI	timm	`0.9.12`	indirect
PyPI	timm	`0.9.8`	indirect
PyPI	timm	`1.0.26`	indirect
PyPI	tinycss2	`1.4.0`	indirect
PyPI	tokenizers	`0.22.2`	indirect
PyPI	tomli	`2.4.1`	indirect
PyPI	torch	`—`	indirect
PyPI	torch	`2.14.0.dev20260625+cu130`	indirect
PyPI	torchao	`0.17.0`	indirect
PyPI	torchao	`0.18.0.dev20260601+cu130`	indirect
PyPI	torchvision	`—`	indirect
PyPI	torchvision	`0.29.0.dev20260626+cu130`	indirect
PyPI	tornado	`6.5.5`	indirect
PyPI	tqdm	`—`	indirect
PyPI	tqdm	`4.67.3`	indirect
PyPI	traitlets	`5.14.3`	indirect
PyPI	transformers	`—`	indirect
PyPI	transformers	`5.5.4`	indirect
PyPI	triton	`2.3.0`	indirect
PyPI	triton	`3.7.1+gitf797708c`	indirect
PyPI	typer	`0.24.1`	indirect
PyPI	typing-extensions	`4.15.0`	indirect
PyPI	typing-inspection	`0.4.2`	indirect
PyPI	typos	`1.45.1`	indirect
PyPI	tzdata	`2026.1`	indirect
PyPI	urllib3	`2.7.0`	indirect
PyPI	virtualenv	`21.2.4`	indirect
PyPI	webencodings	`0.5.1`	indirect
PyPI	wonderwords	`3.0.1`	indirect
PyPI	xxhash	`3.6.0`	indirect
PyPI	yarl	`1.23.0`	indirect
PyPI	zipp	`3.23.1`	indirect

Dependency advisories 0

Installing pypi:torch-tensorrt-rtx@2.13.0 pulls in 11 packages, direct and transitive: 0 carry known advisories, of which 0 are direct dependencies.

No known advisories affect the assessed dependencies.

An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.

Raw JSON report machine-readable

Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.

Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.5.0, schema v0.27.0 — full methodology · metrics wiki.

How one result sits in the wider record: aggregate statistics — PyPI.

Software health index

Score profile

Ownership

Package ecosystems

Metrics by category

Key facts

Data collection warnings

More detail

Related records