Public record
Software health reportschema 0.11.0 · metrics 2.10.0 · 2026-07-16 00:05 UTC

intel / auto-round

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

Python · C++Apache-2.0★ 1,520 stars⑂ 155 forkssince Jan 2024View on GitHub ↗
#int4#quantization#rounding#transformers#vllm#mxfp4#nvfp4#gguf#sglang#llms#vlms#diffusers#omni

intel/auto-round holds a health index of 97 out of 100, placing it in the Exceptional band. It scores highest on Vitality (99/100) and lowest on AI Readiness (60/100). It was last updated today. 3 contributors account for most of its recent work.

97
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.

97
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 85 is calibrated to 97 on the published index scale (record calibration 2026-08-02).

Ownership

Intel® CorporationOrganization
5,420 followers1,344 public repossince Mar 2016

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

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 0 days ago
35.3/36Commit cadence — 51/52 weeks with commits
18/18Commit volume — 758 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_year758
human_commit_share—
days_since_last_push0
active_weeks_last_year51

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 37 releases published
36/36Release recency — latest release 2 days ago
27/27Release cadence — a release every ~16.6 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count37
latest_release_tagv0.14.2
releases_from_tagsno
days_since_latest_release2
mean_days_between_releases16.6
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?

83Excellent · 17% of overall

Popularity & adoption

76Good
How it's scored
51.6/60Stars — 1,520 stars
18.2/25Forks — 155 forks
6.7/15Watchers — 17 watchers
Inputs used
forks155
stars1,520
watchers17
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_badges—
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_services—
has_pull_request_templateyes

Sustainability & Governance

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

86Excellent · 23% of overall

Maintainer resilience (bus factor)

71Good
How it's scored
36/54Bus factor — 3 contributor(s) cover half of all commits
15.5/22.5Commit distribution — top contributor authored 31% of commits
13.5/13.5Contributor breadth — 37 contributors
6/10OpenSSF Scorecard: Contributors — project has 2 contributing companies or organizations -- score normalized to 6
Inputs used
bus_factor3
contributors_sampled37
top_contributor_share0.31

Issue & PR responsiveness

90Excellent
How it's scored
37/42Issue resolution — 88% of issues closed
26.2/30PR acceptance — 1,216/1,392 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
15/15OpenSSF Scorecard: Code-Review — all changesets reviewed
Inputs used
merged_prs1,216
open_issues76
closed_issues560
prs_merged_7d—
prs_decided_7d—
prs_merged_30d—
prs_decided_30d—
issue_closed_ratio0.881
closed_unmerged_prs176
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

100Exceptional
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain — verified-domain status not read for this organization
25/25Owner reach — 5,420 followers of intel
25/25Track record — 1,344 public repos, account ~10 yr old
Inputs used
followers5,420
owner_typeOrganization
is_verified—
owner_loginintel
public_repos1,344
account_age_days3,773
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Engineering Quality

Are baseline engineering and documentation practices in place?

89Excellent · 19% of overall

Engineering practices

92Excellent
How it's scored
24/24CI workflows — 5 workflow(s)
24/24Tests present
16/16Linter config
9.6/9.6Pre-commit hooks
0/6.4.editorconfig
18/20OpenSSF Scorecard: CI-Tests — 29 out of 30 merged PRs checked by a CI test -- score normalized to 9
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configyes

Documentation

85Excellent
How it's scored
30/30README
25/25Documentation directory
0/15Documentation / homepage site
10/10Repository description
10/10Topics — 13 topics
10/10Wiki
Inputs used
topicsint4, quantization, rounding, transformers, vllm, mxfp4, nvfp4, gguf, sglang, llms, vlms, diffusers, omni
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?

70Good · 16% of overall

Security posture

70Good
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
2.2/7.5Branch-Protection — branch protection is not maximal on development and all release branches
2.2/2.5CI-Tests — 29 out of 30 merged PRs checked by a CI test -- score normalized to 9
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
7.5/7.5Code-Review — all changesets reviewed
1.5/2.5Contributors — project has 2 contributing companies or organizations -- score normalized to 6
10/10Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5Dependency-Update-Tool — 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
0/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
4.5/5SAST — SAST tool detected but not run on all commits
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
6.8/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 28 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated16
scorecard_versionv5.5.0
checks_inconclusive2
scorecard_aggregate7
Excluded from scoring (no data or not applicable): Packaging, Signed-Releases. Remaining weights renormalized.

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.

60Moderate · 4% of overall

Agent context & guidance

75Good
How it's scored
45/45Agent instructions — .github/copilot-instructions.md, AGENTS.md, CLAUDE.md
0/15Machine-readable docs (llms.txt)
0/40Legible commit history — no data
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share—
agent_instruction_files.github/copilot-instructions.md, AGENTS.md, CLAUDE.md
agent_instruction_max_bytes2,729
Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.

Verify loop (build / test / typecheck)

52Moderate
How it's scored
0/18One-command bootstrap
22/22Automated tests
11/11Lint / format config
0/11Static type checking
10/10Reproducible environment — Dockerfile
0/10Demonstrated agent practice — no data
0/8Automated maintenance — no data
0/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
Inputs used
has_nixno
has_testsyes
lockfiles—
has_dockerfileyes
typed_languageno
bootstrap_files—
has_devcontainerno
has_linter_configyes
typecheck_configs—
agent_commit_share—
toolchain_manifests—
dependency_bot_commit_share—
Excluded from scoring (no data or not applicable): Demonstrated agent practice, Automated maintenance. Remaining weights renormalized.

Code legibility for models

53Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
52.6/55Manageable file sizes — 25/581 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes1,930,927
source_files_sampled581
oversized_source_files25

Key facts

1,520GitHub stars
37contributors
758commits, last 12 months
0days since last push
37releases
3bus factor
76open issues
PyPIpackage ecosystems

More detail

OpenSSF Scorecard 7.0 / 10
7.0aggregate

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 · 2026-07-16 00:01 UTC

10Binary-Artifactsno binaries found in the repo
3Branch-Protectionbranch protection is not maximal on development and all release branches
9CI-Tests29 out of 30 merged PRs checked by a CI test -- score normalized to 9
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
10Code-Reviewall changesets reviewed
6Contributorsproject has 2 contributing companies or organizations -- score normalized to 6
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate 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
0Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 0
9SASTSAST tool detected but not run on all commits
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
9Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities28 existing vulnerabilities detected
All dependencies 42

Full resolved dependency set from the GitHub dependency graph: 0 direct and 42 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIaccelerate—indirect
PyPIaddict—indirect
PyPIauto-round-lib—indirect
PyPIbitsandbytes—indirect
PyPIclip—indirect
PyPIcompressed-tensors—indirect
PyPIdatasets—indirect
PyPIdiffusers—indirect
PyPIeinops—indirect
PyPIflash-attn—indirect
PyPIgguf—indirect
PyPIgptqmodel—indirect
PyPIimage-reward—indirect
PyPIllmcompressor—indirect
PyPIlm-eval—indirect
PyPImodelscope—indirect
PyPIneural-compressor-pt—indirect
PyPInumba—indirect
PyPInumpy—indirect
PyPIoptimum—indirect
PyPIpackaging—indirect
PyPIpandas—indirect
PyPIparameterized—indirect
PyPIpillow—indirect
PyPIprotobuf—indirect
PyPIpy-cpuinfo—indirect
PyPIpydantic—indirect
PyPIpytest—indirect
PyPIray—indirect
PyPIsentencepiece—indirect
PyPIsetuptools—indirect
PyPIsglang—indirect
PyPItbb—indirect
PyPItiktoken—indirect
PyPItimm—indirect
PyPItorch—indirect
PyPItorchvision—indirect
PyPItqdm—indirect
PyPItransformers—indirect
PyPItriton—indirect
PyPIvllm—indirect
PyPIxformers—indirect
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 intel/auto-round. Read them side by side →

89ModelCloud/GPTQModelLLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.Excellent99ai-dynamo/dynamoA Datacenter Scale Distributed Inference Serving FrameworkExceptional96vllm-project/llm-compressorTransformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLMExceptional78Sahil170595/ChimeraforgePyPI capacity-planning CLI for LLM deployment. pip install chimeraforge.Good63jagmarques/nexusquantTraining-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated.Moderate63RobTand/gridbookOut-of-tree vLLM plugin and open format spec for NVFP4-CB / FP8-CB product-codebook weights — 2-6 bit-per-weight LLM quantization served on native Blackwell tensor cores.Moderate

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 v0.11.0 — full methodology · metrics wiki.

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