Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-08-27 22:49 UTC

NVIDIA / TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

C++Apache-2.0★ 13,294 stars⑂ 2,397 forkssince May 2019View on GitHub ↗
KindLibraryCommand-line toolhow this is determined
#tensorrt#nvidia#deep-learning#inference#gpu-acceleration

NVIDIA/TensorRT holds a health index of 88 out of 100, placing it in the Excellent band. It scores highest on Community & Adoption (88/100) and lowest on Security (40/100). It was last updated 2 days ago. 3 contributors account for most of its recent work.

88
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.

88
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)
VitalityCommunity &AdoptionSustainability &GovernanceEngineeringQualitySecurityAI Readiness

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 74 is calibrated to 88 on the published index scale (record calibration 2026-08-02).

Ownership

NVIDIA CorporationOrganization · verified domain
29,403 followers800 public repossince May 2012

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
PyPIpolygraphy0.53.4258,4771320 days ago—
PyPItensorrt11.2.1.2233,1064828 days agonvidiatensorrtdeeplearninginference
PyPIonnx_graphsurgeon0.6.1510,1268141 days ago—
PyPIpytorch_quantizationpoints to another repo — not scored2.2.11,39351028 days agonvidiadeep-learningmachine-learningsupervised-learningunsupervised-learningreinforcement-learninglogging
PyPIpolygraphy_trtexec0.0.93231099 days ago—

Metrics by category

Vitality

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

78Good · 21% of overall

Development activity

68Good
How it's scored
36/36Push recency — last push 2 days ago
12.5/36Commit cadence — 18/52 weeks with commits
12.9/18Commit volume — 26 commits in the last year
0/10OpenSSF Scorecard: Maintained — no data
Inputs used
commits_last_year26
human_commit_share1
days_since_last_push2
active_weeks_last_year18

Release discipline

92Excellent
How it's scored
27/27Ships releases — 71 releases published
36/36Release recency — latest release 23 days ago
19.8/27Release cadence — a release every ~45.8 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count71
latest_release_tagv11.2
releases_from_tagsno
days_since_latest_release23
mean_days_between_releases45.8

Community & Adoption

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

88Excellent · 17% of overall

Popularity & adoption

97Exceptional
How it's scored
60/60Stars — 13,294 stars
25/25Forks — 2,397 forks
12.2/15Watchers — 157 watchers
Inputs used
forks2,397
stars13,294
watchers157
growth_stateorganic
growth_factor_pct100

Community health

70Good
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (Apache-2.0)
18/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
0/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges3
has_contributingyes
has_issue_templateno
has_code_of_conductno
readme_badge_servicesshields.io
has_pull_request_templateno

Ecosystem adoption (downloads)

100Exceptional
How it's scored
80/80Monthly downloads — 1,001,741 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagespolygraphy, tensorrt, onnx_graphsurgeon, polygraphy_trtexec
dependents—
ecosystemspypi
total_downloads—
monthly_downloads1,001,741
unverified_packages_excluded—
Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.

Sustainability & Governance

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

84Excellent · 23% of overall

Maintainer resilience (bus factor)

72Good
How it's scored
36/54Bus factor — 3 contributor(s) cover half of all commits
15/22.5Commit distribution — top contributor authored 33% of commits
13.5/13.5Contributor breadth — 83 contributors
0/10OpenSSF Scorecard: Contributors — no data
Inputs used
bus_factor3
contributors_sampled83
top_contributor_share0.333

Issue & PR responsiveness

71Good
How it's scored
36.3/42Issue resolution — 86% of issues closed
19.7/30PR acceptance — 327/498 decided PRs merged
4.3/13Newcomer PR acceptance — 1/3 first-time contributors' PRs merged in 30d
0/15OpenSSF Scorecard: Code-Review — no data
Inputs used
merged_prs327
open_issues573
closed_issues3,658
prs_merged_7d1
prs_decided_7d2
prs_merged_30d4
prs_decided_30d6
issue_closed_ratio0.865
closed_unmerged_prs171
first_time_authors_30d2
first_time_prs_merged_30d1
first_time_prs_decided_30d3

Ownership & stewardship

100Exceptional
How it's scored
30/30Ownership backing — organization-owned
20/20Verified domain
25/25Owner reach — 29,403 followers of NVIDIA
25/25Track record — 800 public repos, account ~14 yr old
Inputs used
followers29,403
owner_typeOrganization
is_verifiedyes
owner_loginNVIDIA
public_repos800
account_age_days5,222

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 4 package(s) on pypi
35/35Publish recency — latest publish 20 days ago
20/20Version history — 48 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagespolygraphy, tensorrt, onnx_graphsurgeon, polygraphy_trtexec
ecosystemspypi
any_deprecatedno
min_days_since_publish20

Engineering Quality

Are baseline engineering and documentation practices in place?

74Good · 19% of overall

Engineering practices

80Excellent
How it's scored
24/24CI workflows — 5 workflow(s)
24/24Tests present
16/16Linter config — .pylintrc
0/9.6Pre-commit hooks
0/6.4.editorconfig
0/20OpenSSF Scorecard: CI-Tests — no data
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configno

Documentation

65Good
How it's scored
30/30README
0/25Documentation directory
15/15Documentation / homepage site — https://developer.nvidia.com/tensorrt
10/10Repository description
10/10Topics — 5 topics
0/10Wiki
Inputs used
topicstensorrt, nvidia, deep-learning, inference, gpu-acceleration
has_wikino
homepagehttps://developer.nvidia.com/tensorrt
docs_sitehttps://developer.nvidia.com/tensorrt
has_readmeyes
has_docs_dirno
has_descriptionyes

Security

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

40Weak · 16% of overall

Security posture

25At Risk
How it's scored
0/30Security policy (SECURITY.md)
0/25Dependabot config
25/25Dependency lockfiles — poetry.lock
0/20CodeQL workflow
Inputs used
sourcefile_signals
lockfilespoetry.lock
manifestspython/requirements.txt
has_codeql_workflowno
has_security_policyno
has_dependabot_configno

Dependency advisories

100Exceptional
How it's scored
35/35Direct dependencies free of known advisories — no direct dependency carries a known advisory
25/25Indirect dependencies free of known advisories — no indirect dependency carries a known advisory
0/40No advisories left outstanding — no advisory carries a publication date
Inputs used
sourceosv
advisories0
affected_packages0
assessed_packages3
unassessed_packages0
affected_by_severitynone
direct_affected_packages0
Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the pypi:tensorrt@11.2.1.2 runtime dependency closure — what installing the published package pulls in — 3 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.

76Good · 4% of overall

Agent context & guidance

50Moderate
How it's scored
0/45Agent instructions — no CLAUDE.md / AGENTS.md / editor rules
15/15Machine-readable docs (llms.txt) — llms.txt served by the project website (https://developer.nvidia.com/llms.txt)
34.7/40Legible commit history — 65 of 100 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_urlhttps://developer.nvidia.com/llms.txt
legible_history_share0.65
agent_instruction_files—
agent_instruction_max_bytes—

Verify loop (build / test / typecheck)

80Excellent
How it's scored
18/18One-command bootstrap — quickstart/Makefile, quickstart/SemanticSegmentation/Makefile, tools/Polygraphy/Makefile, tools/onnx-graphsurgeon/Makefile, tools/polygraphy-extension-trtexec/Makefile, tools/pytorch-quantization/docs/Makefile, tools/tensorflow-quantization/docs/Makefile
22/22Automated tests
11/11Lint / format config — .pylintrc
11/11Static type checking — C++ (statically typed)
10/10Reproducible environment — lockfile
0/10Demonstrated agent practice — no agent-authored commits among the last 100
0/8Automated maintenance — no automated dependency updates observed
0/10OpenSSF Scorecard: Pinned-Dependencies — no data
Inputs used
has_nixno
has_testsyes
lockfilespoetry.lock
has_dockerfileno
typed_languageyes
bootstrap_filesquickstart/Makefile, quickstart/SemanticSegmentation/Makefile, tools/Polygraphy/Makefile, tools/onnx-graphsurgeon/Makefile, tools/polygraphy-extension-trtexec/Makefile, tools/pytorch-quantization/docs/Makefile, tools/tensorflow-quantization/docs/Makefile
has_devcontainerno
has_linter_configyes
typecheck_configs—
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0

Code legibility for models

90Excellent
How it's scored
45/45Type-checkable code — C++ (statically typed)
44.9/55Manageable file sizes — 199/1,080 source files over 60KB
Inputs used
primary_languageC++
largest_source_bytes3,041,274
source_files_sampled1,080
oversized_source_files199

Machine-readable interfaces

100Exceptional
How it's scored
0/40API schema (OpenAPI/GraphQL/proto) — not applicable to this kind of software
0/20MCP server — not applicable to this kind of software
40/40Runnable examples — examples, notebooks, samples
Inputs used
example_dirsexamples, notebooks, samples
has_mcp_signalno
api_schema_files—
interfaces_expected_of—
Excluded from scoring (no data or not applicable): API schema (OpenAPI/GraphQL/proto), MCP server. Remaining weights renormalized.

Key facts

13,294GitHub stars
83contributors
26commits, last 12 months
2days since last push
71releases
3bus factor
573open issues
PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • Star history carried forward from 2026-07-21: GitHub restricted the stargazers API to repository admins, so it can no longer be collected. The repository has 13294 stars today.
  • pypi package 'pytorch_quantization' points at a different repository (https://github.com/NVIDIA); excluded from ecosystem scoring
  • Could not fetch pypi package 'tensorflow_quantization' from its registry
  • OpenSSF Scorecard did not return a usable result (killed by SIGKILL — most likely the container's memory limit; 2026/08/27 22:47:16 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 13,169 ★ / 2,397 ⇿
13,169Stars
2,397Forks
33Releases

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.

Only the most recent history is shown — this repository exceeds the collection window, so the earliest history is not captured.

Star history is shown as collected on 2026-07-21. GitHub restricted the stargazers API to repository administrators in July 2026, so this series can no longer be extended; the current star total above remains live.

02,5005,0007,50010,00012,50015,00013,1692,397462022-112024-092026-08
Major 1Minor 16Patch 7

Each point covers 4 days.

Direct dependencies 2
RegistryPackageVersion constraintManifest
PyPIwheel0.45.1python/packaging/pyproject.toml
PyPIsetuptools^80.4.0python/packaging/pyproject.toml
All dependencies 257

Full resolved dependency set from the GitHub dependency graph: 5 direct and 252 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIsetuptools—direct
PyPIsetuptools80.4.0direct
PyPIsetuptools80.9.0direct
PyPIwheel—direct
PyPIwheel0.45.1direct
PyPIabsl-py—indirect
PyPIaccelerate1.2.1indirect
PyPIalabaster0.7.16indirect
PyPIanykeystore0.2indirect
PyPIapex0.9.10devindirect
PyPIargparse—indirect
PyPIbabel2.17.0indirect
PyPIbeautifulsoup44.14.2indirect
PyPIbuild1.0.0indirect
PyPIcertifi2025.10.5indirect
PyPIcharset-normalizer3.4.3indirect
PyPIcolorama0.4.6indirect
PyPIcolored—indirect
PyPIcolored2.3.1indirect
PyPIcolored2.3.2indirect
PyPIcoloredlogs15.0.1indirect
PyPIcontourpy1.3.2indirect
PyPIcontrolnet-aux0.0.6indirect
PyPIcryptacular1.6.2indirect
PyPIcuda-bindings—indirect
PyPIcuda-bindings13.0.2indirect
PyPIcuda-pathfinder1.3.0indirect
PyPIcuda-python—indirect
PyPIcuda-python12.9.0indirect
PyPIcuda-python13.0.2indirect
PyPIcupy-cuda12x—indirect
PyPIcupy-cuda12x13.6.0indirect
PyPIcycler0.12.1indirect
PyPIdiffusers0.35.2indirect
PyPIdocutils0.16indirect
PyPIdocutils0.18.1indirect
PyPIdocutils0.20.1indirect
PyPIeinops0.8.1indirect
PyPIexceptiongroup1.3.0indirect
PyPIfilelock3.20.0indirect
PyPIflatbuffers25.9.23indirect
PyPIfonttools4.60.1indirect
PyPIfsspec2025.9.0indirect
PyPIftfy—indirect
PyPIftfy6.3.1indirect
PyPIfuro2022.4.7indirect
PyPIfuro2024.8.6indirect
PyPIgcloud—indirect
PyPIgoogle-cloud-storage—indirect
PyPIgreenlet3.2.4indirect
PyPIhf-xet1.1.10indirect
PyPIhuggingface-hub0.11.0indirect
PyPIhuggingface-hub0.35.3indirect
PyPIhuggingface-hub0.4.0indirect
PyPIhumanfriendly10.0indirect
PyPIhupper1.12.1indirect
PyPIidna3.10indirect
PyPIimageio2.37.0indirect
PyPIimageio-ffmpeg—indirect
PyPIimageio-ffmpeg0.6.0indirect
PyPIimagesize1.4.1indirect
PyPIimportlib-metadata8.7.0indirect
PyPIiniconfig2.1.0indirect
PyPIjinja23.1.6indirect
PyPIkiwisolver1.4.9indirect
PyPIlazy-loader0.4indirect
PyPImarkdown-it-py3.0.0indirect
PyPImarkupsafe3.0.3indirect
PyPImatplotlib—indirect
PyPImatplotlib3.10.7indirect
PyPImdit-py-plugins0.5.0indirect
PyPImdurl0.1.2indirect
PyPIml-dtypes—indirect
PyPIml-dtypes0.5.3indirect
PyPImpi4py4.1.1indirect
PyPImpmath1.3.0indirect
PyPImyst-parser0.16.1indirect
PyPImyst-parser3.0.1indirect
PyPInccl4py0.1.1indirect
PyPInetworkx3.4.2indirect
PyPInltk3.9.1indirect
PyPInumba—indirect
PyPInumba-cuda—indirect
PyPInumpy—indirect
PyPInumpy1.23.0indirect
PyPInumpy1.23.1indirect
PyPInumpy1.26.4indirect
PyPInumpy2.2.3indirect
PyPInumpy2.2.6indirect
PyPInvidia-cublas-cu1212.8.4.1indirect
PyPInvidia-cuda-cupti-cu1212.8.90indirect
PyPInvidia-cuda-nvrtc-cu1212.8.93indirect
PyPInvidia-cuda-runtime-cu1212.8.90indirect
PyPInvidia-cudnn-cu129.10.2.21indirect
PyPInvidia-cufft-cu1211.3.3.83indirect
PyPInvidia-cufile-cu121.13.1.3indirect
PyPInvidia-curand-cu1210.3.9.90indirect
PyPInvidia-cusolver-cu1211.7.3.90indirect
PyPInvidia-cusparse-cu1212.5.8.93indirect
PyPInvidia-cusparselt-cu120.7.1indirect
PyPInvidia-cutlass-dsl4.5.0indirect
PyPInvidia-modelopt—indirect
PyPInvidia-modelopt0.31.0indirect
PyPInvidia-modelopt0.35.0indirect
PyPInvidia-nccl-cu122.27.3indirect
PyPInvidia-nvjitlink-cu1212.8.93indirect
PyPInvidia-nvtx-cu1212.8.90indirect
PyPInvidia-pyindex—indirect
PyPInvidia-tensorrt—indirect
PyPInvtx—indirect
PyPInvtx0.2.13indirect
PyPIoauthlib3.3.1indirect
PyPIonnx—indirect
PyPIonnx1.13.1indirect
PyPIonnx1.14.0indirect
PyPIonnx1.17.0indirect
PyPIonnx1.18.0indirect
PyPIonnx1.20.0indirect
PyPIonnx1.9.0indirect
PyPIonnx-graphsurgeon—indirect
PyPIonnx-graphsurgeon0.5.2indirect
PyPIonnx-ir0.1.10indirect
PyPIonnxconverter-common1.12.2indirect
PyPIonnxmltools1.11.1indirect
PyPIonnxruntime—indirect
PyPIonnxruntime1.12.1indirect
PyPIonnxruntime1.15.0indirect
PyPIonnxruntime1.18.1indirect
PyPIonnxruntime1.19.2indirect
PyPIonnxruntime1.22.1indirect
PyPIonnxruntime1.24.2indirect
PyPIonnxruntime1.8.1indirect
PyPIonnxruntime-gpu—indirect
PyPIonnxscript—indirect
PyPIonnxscript0.5.4indirect
PyPIopencv-python4.11.0.86indirect
PyPIopencv-python-headless4.8.0.74indirect
PyPIpackaging25.0indirect
PyPIpastedeploy3.1.0indirect
PyPIpbkdf21.3indirect
PyPIpeft0.17.0indirect
PyPIpillow—indirect
PyPIpillow11.3.0indirect
PyPIplaster1.1.2indirect
PyPIplaster-pastedeploy1.0.1indirect
PyPIpluggy1.6.0indirect
PyPIpolygraphy—indirect
PyPIpolygraphy0.49.0indirect
PyPIpolygraphy0.49.22indirect
PyPIpolygraphy0.50.1indirect
PyPIprettytable—indirect
PyPIprotobuf—indirect
PyPIprotobuf3.20.2indirect
PyPIprotobuf3.20.3indirect
PyPIprotobuf6.32.1indirect
PyPIpsutil7.1.0indirect
PyPIpycuda—indirect
PyPIpygments2.19.2indirect
PyPIpyparsing3.2.5indirect
PyPIpyramid2.0.2indirect
PyPIpyramid-mailer0.15.1indirect
PyPIpyreadline33.5.4indirect
PyPIpytest—indirect
PyPIpytest8.4.2indirect
PyPIpytest-console-scripts—indirect
PyPIpytest-rerunfailures—indirect
PyPIpytest-virtualenv—indirect
PyPIpytest-xdist—indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpython-openid2.2.5indirect
PyPIpywin32—indirect
PyPIpyyaml—indirect
PyPIpyyaml6.0.3indirect
PyPIregex2025.9.18indirect
PyPIrepoze-sendmail4.4.1indirect
PyPIrequests2.25.1indirect
PyPIrequests2.32.4indirect
PyPIrequests2.32.5indirect
PyPIrequests2.33.0indirect
PyPIrequests-oauthlib2.0.0indirect
PyPIsafetensors0.6.2indirect
PyPIscikit-image0.25.2indirect
PyPIscipy—indirect
PyPIscipy1.15.3indirect
PyPIsentencepiece—indirect
PyPIsentencepiece0.1.95indirect
PyPIsentencepiece0.1.97indirect
PyPIsentencepiece0.2.1indirect
PyPIsix1.17.0indirect
PyPIsnowballstemmer3.0.1indirect
PyPIsoupsieve2.8indirect
PyPIsphinx4.4.0indirect
PyPIsphinx7.1.2indirect
PyPIsphinx-basic-ng1.0.0b2indirect
PyPIsphinx-glpi-theme—indirect
PyPIsphinxcontrib-applehelp2.0.0indirect
PyPIsphinxcontrib-devhelp2.0.0indirect
PyPIsphinxcontrib-htmlhelp2.1.0indirect
PyPIsphinxcontrib-jsmath1.0.1indirect
PyPIsphinxcontrib-qthelp2.0.0indirect
PyPIsphinxcontrib-serializinghtml2.0.0indirect
PyPIsqlalchemy2.0.44indirect
PyPIsympy1.14.0indirect
PyPIsympy1.9indirect
PyPItabulate—indirect
PyPItensorflow—indirect
PyPItensorflow-gpu2.8.0indirect
PyPItensorrt—indirect
PyPItensorrt-module—indirect
PyPItf2onnx—indirect
PyPItf2onnx1.10.1indirect
PyPItifffile2025.5.10indirect
PyPItimm1.0.20indirect
PyPItokenizers0.21.4indirect
PyPItoml—indirect
PyPItomli2.0.0indirect
PyPItomli2.3.0indirect
PyPItorch—indirect
PyPItorch1.10indirect
PyPItorch1.10.2indirect
PyPItorch1.10.2+cu113indirect
PyPItorch1.11.0indirect
PyPItorch1.11.0+cu113indirect
PyPItorch1.13.1indirect
PyPItorch2.8.0indirect
PyPItorch2.9.1indirect
PyPItorchao0.13.0indirect
PyPItorchvision—indirect
PyPItorchvision0.11.3indirect
PyPItorchvision0.12.0indirect
PyPItorchvision0.23.0indirect
PyPItqdm4.66.4indirect
PyPItqdm4.67.1indirect
PyPItransaction5.0indirect
PyPItransformers4.18.0indirect
PyPItransformers4.20.0indirect
PyPItransformers4.52.4indirect
PyPItranslationstring1.4indirect
PyPItriton—indirect
PyPItriton3.2.0indirect
PyPItriton3.4.0indirect
PyPItriton3.5.0indirect
PyPItyping-extensions4.15.0indirect
PyPIurllib32.5.0indirect
PyPIvelruse1.1.1indirect
PyPIvenusian3.1.1indirect
PyPIvirtualenv—indirect
PyPIwcwidth0.2.14indirect
PyPIwebob1.8.9indirect
PyPIwget—indirect
PyPIwget3.2indirect
PyPIwtforms3.2.1indirect
PyPIwtforms-recaptcha0.3.2indirect
PyPIzipp3.23.0indirect
PyPIzope-deprecation6.0indirect
PyPIzope-interface8.0.1indirect
PyPIzope-sqlalchemy4.0indirect
Dependency advisories 0

Installing pypi:tensorrt@11.2.1.2 pulls in 3 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

Feedback

Spotted something off in this report, or have thoughts to share? Wrong measurements, missed tooling, ideas, questions — anything is welcome. Every message is read and gets a response.

The message is kept through sign-in.

Related records

Inspected repositories sharing catalogue tags or ecosystems with NVIDIA/TensorRT. Read them side by side →

98NVIDIA/TensorRT-LLMTensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.Exceptional94pytorch/TensorRTPyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRTExceptional92triton-inference-server/model_analyzerTriton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Server models.Excellent87NexusGPU/tensor-fusionTensor Fusion is a state-of-the-art GPU virtualization and pooling solution designed to optimize GPU cluster utilization to its fullest potential.Excellent100huggingface/transformers🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. Exceptional99ai-dynamo/dynamoA Datacenter Scale Distributed Inference Serving FrameworkExceptional

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 v2.10.0, schema v0.34.0 — full methodology · metrics wiki.

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