Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-09-13 19:43 UTC

ai-dynamo / aiconfigurator

Offline optimization of your disaggregated Dynamo graph

Python · RustApache-2.0★ 441 stars⑂ 164 forkssince Jul 2025View on GitHub ↗
KindCommand-line toolLibraryhow this is determined

ai-dynamo/aiconfigurator holds a health index of 95 out of 100, placing it in the Exceptional band. It scores highest on Vitality (99/100) and lowest on Security (62/100). It was last updated 4 days ago. 5 contributors account for most of its recent work.

95
overall / 100
Exceptional

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.

95
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 82 is calibrated to 95 on the published index scale (record calibration 2026-08-02).

Ownership

DynamoOrganization
796 followers16 public repossince Mar 2025

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
PyPIaiconfigurator0.11.013,0691529 days agodecodedistributeddynamogpuinferencellmnvidiaprefill
PyPIaiconfigurator-core0.11.013,050229 days ago—

Metrics by category

Vitality

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

99Exceptional · 21% of overall

Development activity

99Exceptional
How it's scored
36/36Push recency — last push 4 days ago
35.3/36Commit cadence — 51/52 weeks with commits
18/18Commit volume — 846 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year846
human_commit_share1
days_since_last_push4
active_weeks_last_year51

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 13 releases published
36/36Release recency — latest release 27 days ago
27/27Release cadence — a release every ~33 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count13
latest_release_tagv0.11.0
releases_from_tagsno
days_since_latest_release27
mean_days_between_releases33
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.

Community & Adoption

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

76Good · 17% of overall

Popularity & adoption

66Good
How it's scored
42.9/60Stars — 441 stars
18.4/25Forks — 164 forks
4.7/15Watchers — 8 watchers
Inputs used
forks164
stars441
watchers8
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

92Excellent
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (Apache-2.0)
18/18CONTRIBUTING guide
13.5/13.5Code of conduct
0/7.2Issue template
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges0
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_services—
has_pull_request_templateyes

Ecosystem adoption (downloads)

69Good
How it's scored
54.9/80Monthly downloads — 13,069 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagesaiconfigurator
dependents—
ecosystemspypi
total_downloads—
monthly_downloads13,069
unverified_packages_excludedaiconfigurator-core
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?

80Excellent · 23% of overall

Maintainer resilience (bus factor)

88Excellent
How it's scored
45.9/54Bus factor — 5 contributor(s) cover half of all commits
19/22.5Commit distribution — top contributor authored 15% of commits
13.5/13.5Contributor breadth — 65 contributors
10/10OpenSSF Scorecard: Contributors — project has 9 contributing companies or organizations
Inputs used
bus_factor5
contributors_sampled65
top_contributor_share0.154

Issue & PR responsiveness

70Good
How it's scored
21/42Issue resolution — 50% of issues closed
23.7/30PR acceptance — 1,156/1,466 decided PRs merged
9.8/13Newcomer PR acceptance — 3/4 first-time contributors' PRs merged in 30d
15/15OpenSSF Scorecard: Code-Review — all changesets reviewed
Inputs used
merged_prs1,156
open_issues59
closed_issues59
prs_merged_7d1
prs_decided_7d3
prs_merged_30d44
prs_decided_30d60
issue_closed_ratio0.5
closed_unmerged_prs310
first_time_authors_30d2
first_time_prs_merged_30d3
first_time_prs_decided_30d4

Ownership & stewardship

63Moderate
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain
20.9/25Owner reach — 796 followers of ai-dynamo
12/25Track record — 16 public repos, account ~1 yr old
Inputs used
followers796
owner_typeOrganization
is_verifiedno
owner_loginai-dynamo
public_repos16
account_age_days559

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 2 package(s) on pypi
35/35Publish recency — latest publish 29 days ago
20/20Version history — 15 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesaiconfigurator, aiconfigurator-core
ecosystemspypi
any_deprecatedno
min_days_since_publish29

Engineering Quality

Are baseline engineering and documentation practices in place?

86Excellent · 19% of overall

Engineering practices

94Exceptional
How it's scored
24/24CI workflows — 21 workflow(s)
24/24Tests present
16/16Linter config — eslint.config.js, pyproject.toml ([tool.ruff])
9.6/9.6Pre-commit hooks
0/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 30 out of 30 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configyes

Documentation

75Good
How it's scored
30/30README
25/25Documentation directory
0/15Documentation / homepage site
10/10Repository description
0/10Topics
10/10Wiki
Inputs used
topics—
has_wikiyes
homepage—
docs_site—
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

62Moderate · 16% of overall

Security posture

53Moderate
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
3.8/7.5Branch-Protection — branch protection is not maximal on development and all release branches
2.5/2.5CI-Tests — 30 out of 30 merged PRs checked by a CI test -- score normalized to 10
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
7.5/7.5Code-Review — all changesets reviewed
2.5/2.5Contributors — project has 9 contributing companies or organizations
10/10Dangerous-Workflow — no dangerous workflow patterns detected
0/7.5Dependency-Update-Tool — no update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5License — license file detected
7.5/7.5Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10
0/5Packaging — no data
0.5/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 1
0/5SAST — SAST tool is not run on all commits -- score normalized to 0
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 30 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated16
scorecard_versionv5.5.0
checks_inconclusive2
scorecard_aggregate5.3
Excluded from scoring (no data or not applicable): Packaging, Signed-Releases. Remaining weights renormalized.

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_packages36
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:aiconfigurator@0.11.0 runtime dependency closure — what installing the published package pulls in — 36 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.

88Excellent · 4% of overall

Agent context & guidance

100Exceptional
How it's scored
45/45Agent instructions — AGENTS.md
15/15Machine-readable docs (llms.txt) — llms.txt served by the project website (https://docs.nvidia.com/llms.txt)
40/40Legible commit history — 100 of 100 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_urlhttps://docs.nvidia.com/llms.txt
legible_history_share1
agent_instruction_filesAGENTS.md
agent_instruction_max_bytes3,663

Verify loop (build / test / typecheck)

78Good
How it's scored
12.6/18One-command bootstrap — Cargo.toml, aic-core/rust/aiconfigurator-core/Cargo.toml, aic-core/rust/tests/public-api/Cargo.toml (toolchain convention, no task runner)
22/22Automated tests
11/11Lint / format config — eslint.config.js, pyproject.toml ([tool.ruff])
11/11Static type checking — aic-core/src/aiconfigurator_core/py.typed
10/10Reproducible environment — Dockerfile, lockfile
10/10Demonstrated agent practice — 50 of the last 100 commits agent-authored or agent-credited
0/8Automated maintenance — no automated dependency updates observed
1/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 1
Inputs used
has_nixno
has_testsyes
lockfilesCargo.lock, uv.lock
has_dockerfileyes
typed_languageno
bootstrap_files—
has_devcontainerno
has_linter_configyes
typecheck_configsaic-core/src/aiconfigurator_core/py.typed
agent_commit_share0.5
toolchain_manifestsCargo.toml, aic-core/rust/aiconfigurator-core/Cargo.toml, aic-core/rust/tests/public-api/Cargo.toml
dependency_bot_commit_share0

Code legibility for models

79Good
How it's scored
27/45Type-checkable code — Python with type-check config (aic-core/src/aiconfigurator_core/py.typed)
51.8/55Manageable file sizes — 44/752 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes295,315
source_files_sampled752
oversized_source_files44

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 — notebooks
Inputs used
example_dirsnotebooks
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

441GitHub stars
65contributors
846commits, last 12 months
4days since last push
13releases
5bus factor
59open issues
crates.io, PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • First-time contributor figures cover 12 of 14 authors (cap 12)

More detail

Star and fork history 0 ★ / 164 ⇿
0Stars
164Forks
12Releases

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.

0408012016020016232025-082026-022026-09
Major 0Minor 10Patch 1
OpenSSF Scorecard 5.3 / 10
5.3aggregate

Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).Scorecard v5.5.0 · 2026-09-13 19:41 UTC

10Binary-Artifactsno binaries found in the repo
5Branch-Protectionbranch protection is not maximal on development and all release branches
10CI-Tests30 out of 30 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
10Code-Reviewall changesets reviewed
10Contributorsproject has 9 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10
n/aPackagingpackaging workflow not detected
1Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 1
0SASTSAST tool is not run on all commits -- score normalized to 0
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities30 existing vulnerabilities detected
Direct dependencies 22
RegistryPackageVersion constraintManifest
PyPIpackaging>=20.0aic-core/pyproject.toml
PyPInumpy>=2.1,<3aic-core/pyproject.toml
PyPIpandas>=2.2.3aic-core/pyproject.toml
PyPIpyarrow>=15.0.0aic-core/pyproject.toml
PyPIpyyaml>=6.0aic-core/pyproject.toml
PyPIscipy>=1.13.1aic-core/pyproject.toml
PyPIaiconfigurator-core==0.12.0pyproject.toml
PyPIjinja2>=3.1.0pyproject.toml
PyPIpackaging>=20.0pyproject.toml
PyPImatplotlib>=3.9.4pyproject.toml
PyPInumpy>=2.1,<3pyproject.toml
PyPIpandas>=2.2.3pyproject.toml
PyPIplotext>=5.3.2,<6pyproject.toml
PyPIplotly>=6.0.1pyproject.toml
PyPIprettytable>=3.16.0pyproject.toml
PyPIpydantic>=2.5pyproject.toml
PyPIpyarrow>=15.0.0pyproject.toml
PyPIpyyaml>=6.0pyproject.toml
PyPItqdm>=4.0.0pyproject.toml
PyPIbokeh—pyproject.toml
PyPInvidia-ml-py—pyproject.toml
PyPImunch>=4.0.0pyproject.toml
All dependencies 184

Full resolved dependency set from the GitHub dependency graph: 28 direct and 156 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIaiconfigurator-core0.12.0direct
PyPIbokeh3.9.0direct
PyPIjinja23.1.6direct
PyPImatplotlib3.10.8direct
PyPImunch4.0.0direct
PyPInumpy—direct
PyPInumpy2.4.6direct
PyPInumpy2.5.2direct
PyPInvidia-ml-py13.595.45direct
PyPIpackaging—direct
PyPIpackaging26.0direct
PyPIpackaging26.3direct
PyPIpandas—direct
PyPIpandas3.0.2direct
PyPIpandas3.0.5direct
PyPIplotext5.3.2direct
PyPIplotly6.6.0direct
PyPIprettytable3.17.0direct
PyPIpyarrow—direct
PyPIpyarrow24.0.0direct
PyPIpyarrow25.0.1direct
PyPIpydantic2.12.5direct
PyPIpyyaml—direct
PyPIpyyaml6.0.3direct
PyPIscipy—direct
PyPIscipy1.17.1direct
PyPIscipy1.18.0direct
PyPItqdm4.67.3direct
crates.ioanyhow1.0.102indirect
crates.iobitflags2.11.1indirect
crates.iocfg-if1.0.4indirect
crates.iocsv1.4.0indirect
crates.iocsv-core0.1.13indirect
crates.ioequivalent1.0.2indirect
crates.ioerrno0.3.14indirect
crates.iofastrand2.4.1indirect
crates.iofoldhash0.1.5indirect
crates.iogetrandom0.4.2indirect
crates.iohashbrown0.15.5indirect
crates.iohashbrown0.17.0indirect
crates.ioheck0.5.0indirect
crates.ioid-arena2.3.0indirect
crates.ioindexmap2.14.0indirect
crates.ioitoa1.0.18indirect
crates.ioleb128fmt0.1.0indirect
crates.iolibc0.2.186indirect
crates.iolinux-raw-sys0.12.1indirect
crates.iolog0.4.29indirect
crates.iomemchr2.8.0indirect
crates.ioonce_cell1.21.4indirect
crates.ioprettyplease0.2.37indirect
crates.ioproc-macro21.0.106indirect
crates.ioquote1.0.45indirect
crates.ior-efi6.0.0indirect
crates.iorustix1.1.4indirect
crates.ioryu1.0.23indirect
crates.iosemver1.0.28indirect
crates.ioserde1.0.228indirect
crates.ioserde_core1.0.228indirect
crates.ioserde_derive1.0.228indirect
crates.ioserde_json1.0.149indirect
crates.ioserde_yaml0.9.34+deprecatedindirect
crates.iosyn2.0.117indirect
crates.iotempfile3.27.0indirect
crates.iothiserror2.0.18indirect
crates.iothiserror-impl2.0.18indirect
crates.iounicode-ident1.0.24indirect
crates.iounicode-xid0.2.6indirect
crates.iounsafe-libyaml0.2.11indirect
crates.iowasip21.0.3+wasi-0.2.9indirect
crates.iowasip30.4.0+wasi-0.3.0-rc-2026-01-06indirect
crates.iowasm-encoder0.244.0indirect
crates.iowasm-metadata0.244.0indirect
crates.iowasmparser0.244.0indirect
crates.iowindows-link0.2.1indirect
crates.iowindows-sys0.61.2indirect
crates.iowit-bindgen0.51.0indirect
crates.iowit-bindgen0.57.1indirect
crates.iowit-bindgen-core0.51.0indirect
crates.iowit-bindgen-rust0.51.0indirect
crates.iowit-bindgen-rust-macro0.51.0indirect
crates.iowit-component0.244.0indirect
crates.iowit-parser0.244.0indirect
crates.iozmij1.0.21indirect
PyPIaiconfigurator0.12.0indirect
PyPIannotated-doc0.0.4indirect
PyPIannotated-types0.7.0indirect
PyPIanyio4.13.0indirect
PyPIasttokens3.0.1indirect
PyPIattrs26.1.0indirect
PyPIcertifi2026.2.25indirect
PyPIcfgv3.5.0indirect
PyPIchardet5.2.0indirect
PyPIcharset-normalizer3.4.7indirect
PyPIclick8.3.1indirect
PyPIcolorama0.4.6indirect
PyPIcontourpy1.3.3indirect
PyPIcoverage7.13.5indirect
PyPIcycler0.12.1indirect
PyPIdataproperty1.1.0indirect
PyPIdateparser1.4.1indirect
PyPIdecorator5.2.1indirect
PyPIdistlib0.4.0indirect
PyPIexecnet2.1.2indirect
PyPIexecuting2.2.1indirect
PyPIfastapi0.135.3indirect
PyPIfastjsonschema2.21.2indirect
PyPIfilelock3.25.2indirect
PyPIfonttools4.62.1indirect
PyPIh110.16.0indirect
PyPIhttmock1.4.0indirect
PyPIidentify2.6.18indirect
PyPIidna3.11indirect
PyPIimport-ipynb0.2indirect
PyPIiniconfig2.3.0indirect
PyPIipython9.12.0indirect
PyPIipython9.16.1indirect
PyPIipython-pygments-lexers1.1.1indirect
PyPIjedi0.19.2indirect
PyPIjsonschema4.26.0indirect
PyPIjsonschema-specifications2025.9.1indirect
PyPIjupyter-core5.9.1indirect
PyPIkiwisolver1.5.0indirect
PyPImarkupsafe3.0.3indirect
PyPImatplotlib-inline0.2.1indirect
PyPImaturin—indirect
PyPImbstrdecoder1.1.4indirect
PyPInarwhals2.18.1indirect
PyPInbformat5.10.4indirect
PyPInodeenv1.10.0indirect
PyPIorjson3.11.8indirect
PyPIparso0.8.6indirect
PyPIpathvalidate3.3.1indirect
PyPIpexpect4.9.0indirect
PyPIpillow12.2.0indirect
PyPIplatformdirs4.9.4indirect
PyPIpluggy1.6.0indirect
PyPIpre-commit4.3.0indirect
PyPIprometheus-api-client0.6.0indirect
PyPIprompt-toolkit3.0.52indirect
PyPIpsutil7.2.2indirect
PyPIptyprocess0.7.0indirect
PyPIpure-eval0.2.3indirect
PyPIpydantic-core2.41.5indirect
PyPIpygments2.20.0indirect
PyPIpyparsing3.3.2indirect
PyPIpytablewriter1.2.1indirect
PyPIpytest9.1.1indirect
PyPIpytest-asyncio1.3.0indirect
PyPIpytest-cov7.1.0indirect
PyPIpytest-md-report0.8.0indirect
PyPIpytest-mock3.15.1indirect
PyPIpytest-split0.11.0indirect
PyPIpytest-timeout2.4.0indirect
PyPIpytest-xdist3.8.0indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpython-discovery1.2.1indirect
PyPIpytz2026.1.post1indirect
PyPIreferencing0.37.0indirect
PyPIregex2026.5.9indirect
PyPIrequests2.34.2indirect
PyPIrpds-py0.30.0indirect
PyPIruff0.14.1indirect
PyPIsetuptools82.0.1indirect
PyPIsix1.17.0indirect
PyPIstack-data0.6.3indirect
PyPIstarlette0.52.1indirect
PyPItabledata1.3.4indirect
PyPItcolorpy0.1.7indirect
PyPItomli2.4.1indirect
PyPItornado6.5.5indirect
PyPItraitlets5.14.3indirect
PyPItypepy1.3.4indirect
PyPItyping-extensions4.15.0indirect
PyPItyping-inspection0.4.2indirect
PyPItzdata2025.3indirect
PyPItzdata2026.3indirect
PyPItzlocal5.4.3indirect
PyPIurllib32.7.0indirect
PyPIuv0.11.3indirect
PyPIuvicorn0.42.0indirect
PyPIvirtualenv21.2.0indirect
PyPIwcwidth0.6.0indirect
PyPIxyzservices2026.3.0indirect
Dependency advisories 0

Installing pypi:aiconfigurator@0.11.0 pulls in 36 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 ai-dynamo/aiconfigurator. Read them side by side →

99ai-dynamo/dynamoA Datacenter Scale Distributed Inference Serving FrameworkExceptional95ai-dynamo/modelexpressModel Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and improve overall performance.Exceptional95NVIDIA/nvcfPlatform for deploying and routing GPU-accelerated inference, streaming, and batch workloads at scale.Exceptional94utkuozdemir/nvidia_gpu_exporterNvidia GPU exporter for prometheus using nvidia-smi binary OR using NVMLExceptional99vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMsExceptional98sgl-project/sglangSGLang is a high-performance serving framework for large language models and multimodal models.Exceptional

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.