Registro públicoExcelente
Informe de salud del softwareesquema 0.27.0 · métricas 2.3.1 · 2026-08-01 04:48 UTC
mobilint / mblt-model-zoo
Mobilint Model Zoo Project
mobilint/mblt-model-zoo tiene un índice de salud de 80 sobre 100, lo que lo sitúa en la banda Excelente. Su puntuación más alta es Vitality (94/100) y la más baja, Community & Adoption (35/100). Se actualizó por última vez hoy. 2 personas concentran la mayor parte del trabajo reciente.
80
global / 100Índice de salud del software
Las métricas se agrupan en categorías ponderadas sobre una escala estandarizada de 1 a 100. El resultado global parte de su media ponderada, calibrada contra la distribución del registro público para que las bandas tengan significado percentil; cuando la evidencia pública activa la Política de Jurisdicciones de Alto Riesgo, la calificación se ajusta y recibe un límite «En riesgo» de 34.
80
Excepcional93-100El nivel más alto del registro (≈ el 5% superior); cumple prácticamente todos los criterios evaluados
Excelente80-92Sólido en todos los frentes; carencias menores
Bueno65-79Saludable; carencias limitadas y manejables
Moderado50-64Aceptable con carencias notables; se recomienda revisión
Débil35-49Debilidades sustanciales en varias áreas
En riesgo20-34Debilidades significativas; su adopción exige cautela
Crítico1-19Problemas graves (proyecto abandonado, un solo mantenedor, sin higiene)
Perfil de puntuación
Cada eje es una categoría. La forma importa más que la media: un proyecto sano llena toda la figura, mientras que un perfil de picos y cráteres indica que la fortaleza en una dimensión enmascara el riesgo en otra.
El resultado global ponderado 68 se calibra a 80 en la escala publicada del índice (calibración del registro 2026-08-02).
Titularidad
Mobilint, Inc.Organización
24 seguidores20 repositorios públicosdesde dic 2020
Este repositorio está respaldado por una organización: una custodia compartida y responsable que puede sobrevivir a cualquier mantenedor individual.
Ecosistemas de paquetes
| Registro | Paquete | Versión | Descargas / mes | Versiones | Última publicación | Etiquetas |
|---|---|---|---|---|---|---|
| PyPI | mblt-model-zoo | 2.3.0 | - | 31 | hace 0 días | quantizationnpumodel-zoopre-quantized-modelsinferencemobilintmbltariesregulusqb |
Métricas por categoría
Vitalidad
¿Está vivo el proyecto: se escribe código y se publican versiones?
94
Actividad de desarrollo
90Excelente
Cómo se puntúa
| 36/36 | Recencia de push — último push hace 0 días |
| 26.3/36 | Cadencia de commits — 38/52 semanas con commits |
| 18/18 | Volumen de commits — 118 commits en el último año |
| 10/10 | OpenSSF Scorecard: Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
Datos de entrada utilizados
| commits_last_year | 118 |
| human_commit_share | 1 |
| days_since_last_push | 0 |
| active_weeks_last_year | 38 |
Disciplina de publicación
100Excepcional
Cómo se puntúa
| 27/27 | Publica versiones — 30 versiones publicadas |
| 36/36 | Recencia de las versiones — última versión hace 0 días |
| 27/27 | Cadencia de publicación — una versión cada ~11,1 días |
| 0/10 | OpenSSF Scorecard: Signed-Releases — sin datos |
Datos de entrada utilizados
| releases_count | 30 |
| latest_release_tag | v2.3.0 |
| releases_from_tags | no |
| days_since_latest_release | 0 |
| mean_days_between_releases | 11,1 |
Excluidos de la puntuación (sin datos o no aplicable): OpenSSF Scorecard: Signed-Releases. Los pesos restantes se han renormalizado.
Comunidad y Adopción
¿Tiene el proyecto usuarios, descargas, atención y unas condiciones acogedoras para quienes contribuyen?
35
Popularidad y adopción
22En riesgo
Cómo se puntúa
| 21.8/60 | Estrellas — 23 estrellas |
| 0/25 | Forks — 1 forks |
| 0/15 | Observadores — 2 observadores |
Datos de entrada utilizados
| forks | 1 |
| stars | 23 |
| watchers | 2 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Salud de la comunidad
50Moderado
Cómo se puntúa
| 22.5/22.5 | README |
| 22.5/22.5 | Licencia — licencia reconocida (BSD-3-Clause) |
| 0/18 | Guía CONTRIBUTING |
| 0/13.5 | Código de conducta |
| 0/7.2 | Plantilla de issues |
| 0/6.3 | Plantilla de PR |
Datos de entrada utilizados
| has_readme | sí |
| has_license | sí |
| readme_badges | — |
| has_contributing | no |
| has_issue_template | no |
| has_code_of_conduct | no |
| readme_badge_services | — |
| has_pull_request_template | no |
Sostenibilidad y Gobernanza
¿Sobrevivirá el proyecto a sus personas: factor bus, capacidad de respuesta, quién lo respalda y mantenimiento del paquete?
71
Cómo se puntúa
| 25.2/54 | Factor bus — la mitad de los commits recae en 2 contribuyente(s) |
| 13/22.5 | Distribución de commits — el principal contribuyente firma el 42% de los commits |
| 10.8/13.5 | Amplitud de contribuyentes — 8 contribuyentes |
| 0/10 | OpenSSF Scorecard: Contributors — project has 0 contributing companies or organizations -- score normalized to 0 |
Datos de entrada utilizados
| bus_factor | 2 |
| contributors_sampled | 8 |
| top_contributor_share | 0,422 |
Capacidad de respuesta a issues y PR
84Excelente
Cómo se puntúa
| 42/42 | Resolución de issues — 100% de issues cerradas |
| 29.4/30 | Aceptación de PR — 99/101 PR decididos fusionados |
| 0/13 | Newcomer PR acceptance — ningún PR de un contribuyente primerizo decidido en 30 d |
| 1.5/15 | OpenSSF Scorecard: Code-Review — Found 4/30 approved changesets -- score normalized to 1 |
Datos de entrada utilizados
| merged_prs | 99 |
| open_issues | 0 |
| closed_issues | 1 |
| prs_merged_7d | — |
| prs_decided_7d | — |
| prs_merged_30d | — |
| prs_decided_30d | — |
| issue_closed_ratio | 1 |
| closed_unmerged_prs | 2 |
| first_time_authors_30d | — |
| first_time_prs_merged_30d | — |
| first_time_prs_decided_30d | — |
Excluidos de la puntuación (sin datos o no aplicable): newcomer_pr_acceptance. Los pesos restantes se han renormalizado.
Propiedad y custodia
61Moderado
Cómo se puntúa
| 30/30 | Respaldo de la propiedad — propiedad de una organización |
| 0/20 | Dominio verificado |
| 10.1/25 | Alcance del propietario — 24 seguidores de mobilint |
| 20.9/25 | Trayectoria — 20 repos públicos, cuenta de ~5 años |
Datos de entrada utilizados
| followers | 24 |
| owner_type | Organization |
| is_verified | — |
| owner_login | mobilint |
| public_repos | 20 |
| account_age_days | 2055 |
Mantenimiento de paquetes
100Excepcional
Cómo se puntúa
| 25/25 | Publicado y resoluble — 1 paquete(s) en pypi |
| 35/35 | Recencia de publicación — última publicación hace 0 días |
| 20/20 | Historial de versiones — 31 versiones en el registro |
| 20/20 | No obsoleto — activo, ni obsoleto ni retirado |
Datos de entrada utilizados
| packages | mblt-model-zoo |
| ecosystems | pypi |
| any_deprecated | no |
| min_days_since_publish | 0 |
Calidad de Ingeniería
¿Existen unas prácticas mínimas de ingeniería y documentación?
77
Prácticas de ingeniería
78Bueno
Cómo se puntúa
| 24/24 | Flujos de trabajo de CI — 2 flujo(s) de trabajo |
| 24/24 | Pruebas presentes |
| 16/16 | Configuración de linter |
| 9.6/9.6 | Hooks de pre-commit |
| 0/6.4 | .editorconfig |
| 4/20 | OpenSSF Scorecard: CI-Tests — 7 out of 26 merged PRs checked by a CI test -- score normalized to 2 |
Datos de entrada utilizados
| has_ci | sí |
| has_tests | sí |
| has_editorconfig | no |
| has_linter_config | sí |
| has_precommit_config | sí |
Documentación
75Bueno
Cómo se puntúa
| 30/30 | README |
| 0/25 | Directorio de documentación |
| 15/15 | Sitio de documentación / página del proyecto — https://www.mobilint.com/ |
| 10/10 | Descripción del repositorio |
| 10/10 | Topics — 7 topics |
| 10/10 | Wiki |
Datos de entrada utilizados
| topics | ai-accelerators, edge-ai, quantization, mobilint, computer-vision, quantized-neural-networks, transformer |
| has_wiki | sí |
| homepage | https://www.mobilint.com/ |
| has_readme | sí |
| has_docs_dir | no |
| has_description | sí |
Seguridad
¿Son sólidas las prácticas visibles de seguridad y de cadena de suministro, sin exposición jurisdiccional de alto riesgo sin resolver?
53
Postura de seguridad
53Moderado
Cómo se puntúa
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — sin datos |
| 0.5/2.5 | CI-Tests — 7 out of 26 merged PRs checked by a CI test -- score normalized to 2 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 0.8/7.5 | Code-Review — Found 4/30 approved changesets -- score normalized to 1 |
| 0/2.5 | Contributors — project has 0 contributing companies or organizations -- score normalized to 0 |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.5/2.5 | Licencia — license file detected |
| 7.5/7.5 | Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 5/5 | Packaging — packaging workflow detected |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — sin datos |
| 6.8/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 7.5/7.5 | Vulnerabilities — 0 existing vulnerabilities detected |
Datos de entrada utilizados
| source | openssf_scorecard |
| checks_evaluated | 16 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 2 |
| scorecard_aggregate | 5,3 |
Excluidos de la puntuación (sin datos o no aplicable): branch_protection, signed_releases. Los pesos restantes se han renormalizado.
Preparación para IA
¿Hasta qué punto está el repositorio preparado para desarrollarse y mantenerse con agentes de codificación de IA? Tiene un peso deliberadamente pequeño (4%): las herramientas para agentes son una señal real de mantenimiento, pero un repositorio sin ninguna puede alcanzar igualmente 100/100.
60
Contexto y guía para agentes
85Excelente
Cómo se puntúa
| 45/45 | Instrucciones para agentes — AGENTS.md, CLAUDE.md |
| 0/15 | Documentación legible por máquinas (llms.txt) |
| 40/40 | Historial de commits legible — 84 de 100 commits humanos declaran su intención (asunto estructurado o cuerpo explicativo) |
Datos de entrada utilizados
| has_llms_txt | no |
| legible_history_share | 0,84 |
| agent_instruction_files | AGENTS.md, CLAUDE.md |
| agent_instruction_max_bytes | 15.421 |
Cómo se puntúa
| 0/18 | Arranque con un solo comando |
| 22/22 | Pruebas automatizadas |
| 11/11 | Configuración de lint / formato |
| 0/11 | Verificación estática de tipos |
| 0/10 | Entorno reproducible |
| 10/10 | Práctica demostrada con agentes — 11 de los últimos 100 commits con autoría o crédito de agente |
| 0/8 | Mantenimiento automatizado — no se observan actualizaciones automáticas de dependencias |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
Datos de entrada utilizados
| has_nix | no |
| has_tests | sí |
| lockfiles | — |
| has_dockerfile | no |
| typed_language | no |
| bootstrap_files | — |
| has_devcontainer | no |
| has_linter_config | sí |
| typecheck_configs | — |
| agent_commit_share | 0,11 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
Legibilidad del código para modelos
53Moderado
Cómo se puntúa
| 0/45 | Código verificable por tipos — Python sin configuración de verificación de tipos |
| 53.3/55 | Tamaños de archivo manejables — 11/352 archivos fuente de más de 60 KB |
Datos de entrada utilizados
| primary_language | Python |
| largest_source_bytes | 167.903 |
| source_files_sampled | 352 |
| oversized_source_files | 11 |
Datos clave
23estrellas de GitHub
8contribuidores
118commits en los últimos 12 meses
0días desde el último push
30versiones publicadas
2factor bus
0issues abiertas
PyPIecosistemas de paquetes
Advertencias de recopilación de datos
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
- deps.dev does not index pypi:mblt-model-zoo@2.3.0; advisories assessed against the repository dependency graph instead
- No resolved dependencies carried a version and a supported ecosystem
Más detalle
OpenSSF Scorecard 5.3 / 10
5.3agregado
Evaluación de seguridad independiente y agnóstica en cuanto a herramientas, procedente del proyecto de código abierto OpenSSF Scorecard. Cada comprobación premia una práctica de seguridad, no la herramienta de un proveedor concreto. Las comprobaciones que Scorecard no pudo determinar se marcan como n/d y se excluyen de la puntuación de seguridad (nunca se cuentan como cero).
| 10 | Binary-Artifacts | no binaries found in the repo |
| n/d | Branch-Protection | internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md |
| 2 | CI-Tests | 7 out of 26 merged PRs checked by a CI test -- score normalized to 2 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 1 | Code-Review | Found 4/30 approved changesets -- score normalized to 1 |
| 0 | Contributors | project has 0 contributing companies or organizations -- score normalized to 0 |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 10 | License | license file detected |
| 10 | Maintained | 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10 |
| 10 | Packaging | packaging workflow detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| n/d | Signed-Releases | no releases found |
| 9 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 10 | Vulnerabilities | 0 existing vulnerabilities detected |
Dependencias directas 15
| Registro | Paquete | Restricción de versión | Manifiesto |
|---|---|---|---|
| PyPI | mobilint-qb-runtime | >=1.2.0 | pyproject.toml |
| PyPI | numpy | >=1.26.0 | pyproject.toml |
| PyPI | torch | >=2.4.1 | pyproject.toml |
| PyPI | opencv-python | >=4.11.0.86 | pyproject.toml |
| PyPI | pillow | >=11.1.0 | pyproject.toml |
| PyPI | faster-coco-eval | — | pyproject.toml |
| PyPI | huggingface-hub | — | pyproject.toml |
| PyPI | scipy | — | pyproject.toml |
| PyPI | requests | >=2.32.0 | pyproject.toml |
| PyPI | gdown | >=5.2.0 | pyproject.toml |
| PyPI | tqdm | — | pyproject.toml |
| PyPI | mblt-tracker | >=1.0.1 | pyproject.toml |
| PyPI | PyYAML | — | pyproject.toml |
| PyPI | matplotlib | — | pyproject.toml |
| PyPI | cityscapesScripts | — | pyproject.toml |
Todas las dependencias 23
Conjunto completo de dependencias resueltas según el grafo de dependencias de GitHub: 8 paquetes directos y 15 indirectos (transitivos). El cierre transitivo es completo cuando el repositorio incluye un lockfile.
| Registro | Paquete | Versión | Relación |
|---|---|---|---|
| PyPI | gdown | — | directa |
| PyPI | mblt-tracker | — | directa |
| PyPI | mobilint-qb-runtime | — | directa |
| PyPI | numpy | — | directa |
| PyPI | opencv-python | — | directa |
| PyPI | pillow | — | directa |
| PyPI | requests | — | directa |
| PyPI | torch | — | directa |
| PyPI | anyascii | — | indirecta |
| PyPI | datasets | — | indirecta |
| PyPI | g2p-en | — | indirecta |
| PyPI | g2pkk | — | indirecta |
| PyPI | jamo | — | indirecta |
| PyPI | jiwer | — | indirecta |
| PyPI | librosa | — | indirecta |
| PyPI | numba | — | indirecta |
| PyPI | pre-commit | — | indirecta |
| PyPI | pytest | — | indirecta |
| PyPI | python-mecab-ko | — | indirecta |
| PyPI | qbcompiler | — | indirecta |
| PyPI | setuptools | — | indirecta |
| PyPI | transformers | — | indirecta |
| PyPI | unidic | — | indirecta |
Avisos de dependencias sin evaluar
El cotejo de avisos no pudo ejecutarse para este informe: No resolved dependencies carried a version and a supported ecosystem
Informe JSON sin procesar legible por máquina
{
"data": {
"repo": {
"topics": [
"ai-accelerators",
"edge-ai",
"quantization",
"mobilint",
"computer-vision",
"quantized-neural-networks",
"transformer"
],
"is_fork": false,
"size_kb": 7607,
"has_wiki": true,
"homepage": "https://www.mobilint.com/",
"languages": {
"Shell": 4178,
"Python": 3364261
},
"pushed_at": "2026-08-01T04:42:21Z",
"created_at": "2025-03-31T04:23:31Z",
"owner_type": "Organization",
"updated_at": "2026-08-01T04:40:32Z",
"description": "Mobilint Model Zoo Project",
"is_archived": false,
"is_disabled": false,
"license_spdx": "BSD-3-Clause",
"default_branch": "master",
"license_spdx_raw": "BSD-3-Clause",
"primary_language": "Python",
"significant_languages": [
"Python"
]
},
"owner": {
"blog": "http://www.mobilint.com",
"name": "Mobilint, Inc.",
"type": "Organization",
"login": "mobilint",
"company": null,
"location": "Korea, South",
"followers": 24,
"avatar_url": "https://avatars.githubusercontent.com/u/76028030?v=4",
"created_at": "2020-12-15T04:43:56Z",
"is_verified": null,
"public_repos": 20,
"account_age_days": 2055
},
"license": {
"state": "standard",
"spdx_id": "BSD-3-Clause",
"raw_spdx": "BSD-3-Clause",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v2.3.0",
"kind": "minor",
"published_at": "2026-08-01T04:42:21Z"
},
{
"tag": "v2.2.2",
"kind": "patch",
"published_at": "2026-07-24T08:25:38Z"
},
{
"tag": "v2.2.1",
"kind": "patch",
"published_at": "2026-07-15T05:03:01Z"
},
{
"tag": "v2.2.0",
"kind": "minor",
"published_at": "2026-07-13T05:07:26Z"
},
{
"tag": "v2.1.0",
"kind": "minor",
"published_at": "2026-07-04T13:26:43Z"
},
{
"tag": "v2.0.0",
"kind": "major",
"published_at": "2026-07-01T08:41:29Z"
},
{
"tag": "v1.5.1",
"kind": "patch",
"published_at": "2026-05-12T02:29:06Z"
},
{
"tag": "v1.5.0",
"kind": "minor",
"published_at": "2026-05-08T04:48:44Z"
},
{
"tag": "v1.4.2",
"kind": "patch",
"published_at": "2026-04-27T03:46:09Z"
},
{
"tag": "v1.4.1",
"kind": "patch",
"published_at": "2026-04-23T09:27:16Z"
},
{
"tag": "v1.4.0",
"kind": "minor",
"published_at": "2026-04-22T01:06:35Z"
},
{
"tag": "v1.3.1",
"kind": "patch",
"published_at": "2026-04-20T01:26:54Z"
},
{
"tag": "v1.3.0",
"kind": "minor",
"published_at": "2026-04-10T01:16:32Z"
},
{
"tag": "v1.2.2",
"kind": "patch",
"published_at": "2026-04-07T02:22:09Z"
},
{
"tag": "v1.2.1",
"kind": "patch",
"published_at": "2026-04-05T00:34:40Z"
},
{
"tag": "v1.2.0",
"kind": "minor",
"published_at": "2026-04-03T08:58:49Z"
},
{
"tag": "v1.1.0",
"kind": "minor",
"published_at": "2026-04-03T04:25:50Z"
},
{
"tag": "v1.0.0",
"kind": "major",
"published_at": "2026-02-27T09:19:02Z"
},
{
"tag": "v0.5.0",
"kind": "minor",
"published_at": "2026-01-30T04:31:05Z"
},
{
"tag": "v0.4.3",
"kind": "patch",
"published_at": "2025-11-25T05:27:25Z"
},
{
"tag": "v0.4.2",
"kind": "patch",
"published_at": "2025-11-20T08:58:44Z"
},
{
"tag": "v0.4.1",
"kind": "patch",
"published_at": "2025-11-20T06:46:32Z"
},
{
"tag": "v0.4.0",
"kind": "minor",
"published_at": "2025-11-10T08:19:26Z"
},
{
"tag": "v0.3.5",
"kind": "patch",
"published_at": "2025-11-10T05:42:01Z"
},
{
"tag": "v0.3.4",
"kind": "patch",
"published_at": "2025-11-10T05:27:30Z"
},
{
"tag": "v0.3.3",
"kind": "patch",
"published_at": "2025-10-24T04:43:12Z"
},
{
"tag": "v0.3.2",
"kind": "patch",
"published_at": "2025-08-12T07:19:08Z"
},
{
"tag": "v0.0.3.1",
"kind": "other",
"published_at": "2025-08-06T05:38:04Z"
},
{
"tag": "v0.0.3",
"kind": "patch",
"published_at": "2025-08-01T05:04:29Z"
},
{
"tag": "v0.0.2",
"kind": "patch",
"published_at": "2025-06-12T08:19:17Z"
}
],
"recent_commits": [
{
"oid": "a94608be561e3e076eb03ee2545547aa3145f66d",
"body": "…#93)\n\n* feat: add MRoPE support for Qwen3-VL and refactor image processor\n\n- Add MobilintQwen3VLRotaryEmbedding with pre-computed position table\n and 3-D (temporal/height/width) dimension masks for MRoPE\n- Integrate rotary embeddings into MobilintQwen3VLTextModel and pass\n position_embeddings thr\n[…]\n) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: eungyung <eungyung@mobilint.com>\nCo-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>\nCo-authored-by: beomsu <beomsu@mobilint.com>",
"is_bot": false,
"headline": "feat(qwen3-vl): MRoPE + dynamic vision 지원 및 transformers 4.x/5.x 호환 (…",
"author_name": "eungyung",
"author_login": "keg9335",
"committed_at": "2026-08-01T04:40:27Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "59b006439b2c3dd1dcaf9fb1a73cfc48ed23c822",
"body": "* feat: Add comprehensive SKILL.md and CLAUDE.md for Mobilint Model Zoo guidance\n\n* feat: Organize NYU Depth dataset and update related documentation for validation pairs\n\n* depth onnx update\n\n* ade organizer added\n\n* feat: expand vision model metadata\n\n* semantic segmentation ade20k update\n\n* inher\n[…]\nt(vision): validate baked semantic class IDs as finite, integral, and in-range before dtype conversion\n\n* feat(workflow): update code review workflow to include synchronize event and clean up comments",
"is_bot": false,
"headline": "feat(vision): add dense model workflows (#101)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-30T06:54:59Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "097ee93002b9a5cbc489fdf5f46a4d87bd713382",
"body": "* Add batch inference path for VLM\n\n* Refactor VLM tests\n\n* Update test for Qwen3VL Batch16\n\n* Add log\n\n* Add target_clusters expansion in target_cores getter\n\nWhen target_cores is not explicitly set, expand target_clusters into all\nfour cores per cluster so `target_clusters=[0, 1]` under single cor\n[…]\n[0] == aggregate across all four\nefficiency keys.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: Qwen3-VL 배치 추론 지원 및 tps CLI 정합성 개선 (#102)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-07-30T03:42:09Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "4457a4a49663a7285d06ef720de7b7345fdadb16",
"body": "…#100)\n\nscale_coords computed its own inline letterbox padding with a fractional\nformula ((img1 - round(img0*gain)) / 2), while scale_boxes and scale_rboxes\nuse compute_ratio_pad (round(... - 0.1) = the integer pad copyMakeBorder\nactually applies in LetterBox). Keypoints were therefore un-letterboxe\n[…]\ntio/pad as the applied letterbox. Sub-pixel consistency fix; not\nrelated to the earlier pose regression (that was the NMS square-dispatch bug).\n\nCo-authored-by: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(postprocess): align scale_coords pad with scale_boxes/letterbox (…",
"author_name": "Sunghoon-mobilint",
"author_login": "Sunghoon-mobilint",
"committed_at": "2026-07-29T04:50:46Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "239bca5545410a288599883b4f91cc9a18faba4c",
"body": "…n LM head\"\n\nThis reverts commit 854f54b1979178941d91c45c14a6b565ea7aebf7.",
"is_bot": false,
"headline": "Revert \"feat(transformers): use all K logits from a static multi-toke…",
"author_name": "Sunghoon Im",
"author_login": "Sunghoon-mobilint",
"committed_at": "2026-07-29T04:23:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "854f54b1979178941d91c45c14a6b565ea7aebf7",
"body": "`_mxq_supports_all_logits()` answers \"is the output token axis dynamic\", and\nevery caller treats a False as \"last-token-only\". That collapses a real\ndistinction: a graph compiled with `logits_to_keep=K` has a *static* axis of K,\nso the probe reports False and the non-default request falls to the Pat\n[…]\n absolute\nposition into each row, so an off-by-one in the row/position mapping surfaces as\nNaN or a wrong position instead of a plausible number.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(transformers): use all K logits from a static multi-token LM head",
"author_name": "Sunghoon Im",
"author_login": "Sunghoon-mobilint",
"committed_at": "2026-07-28T09:54:50Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "b275d21a2ea48947c7d4ea2465d27f0c5f2109dc",
"body": "Updated pull request review types and adjusted permissions.",
"is_bot": false,
"headline": "Modify code review workflow settings",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-27T02:50:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c0f7f8567913a37b72b232f4b139e24a438dc27a",
"body": "* fix: normalize anchorless output layout\n\n* bump version",
"is_bot": false,
"headline": "fix: normalize anchorless output layout (#99)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-24T08:24:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7fad92d9fe56d5cecb2ca4379150317bedd61afb",
"body": "… postprocessing methods (#98)",
"is_bot": false,
"headline": "feat: Enhance dual_topk function to support logits and update related…",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-16T09:09:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1f23482689d11be45814af777658c7297572b051",
"body": "…… (#97)\n\n* fix: Update CenterCrop to use a tuple for border value and enhance Resize docstring for clarity\n\n* fix: Update Resize class to improve type handling and error messages for input images",
"is_bot": false,
"headline": "fix: Update CenterCrop to use a tuple for border value and enhance Re…",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-16T01:28:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bc08965a4256f65f997df10eeb8fe07ff8740ff1",
"body": "…… (#96)\n\n* feat: Default ONNX Runtime to CPU provider and update related documentation\n\n* fix: remove unused postprocess_kwargs in run_vision_inference and update related test\n\n* fix: update ONNX Runtime provider preference to default to CPUExecutionProvider in documentation",
"is_bot": false,
"headline": "feat: Default ONNX Runtime to CPU provider and update related documen…",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-15T07:04:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3b0ed39e5720b7f78ac03b931c1011abe1f53f21",
"body": "* fix: propagate prefill_chunk_size through text-only Mobilint LM generation\n\n텍스트 전용 Mobilint causal LM 클래스는 MRO 상 MobilintModelMixin이\nMobilintGenerationMixin보다 앞에 위치하기 때문에, generate()가 부르는\nprepare_inputs_for_generation이 GenerationMixin 구현을 타서\ncount_npu_time / prefill_chunk_size 등 벤치마크 kwargs가 llm_f\n[…]\nng the chunked and single-shot no-cache\nbranches.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "Fix runtime propagation of npu_prefill_chunk_size (2.2.1) (#95)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-07-15T05:02:27Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "733918d711e81179bfa925d3f87e7fedce48b222",
"body": "* feat: Add support for creating reproducible subsets in COCO, DOTAv1, and ImageNet organizers\n\n* feat: Update dataset organization scripts to create flat deterministic subsets for COCO, DOTAv1, and ImageNet\n\n* feat: Update model configuration files to adjust resize dimensions and add qbcompiler dep\n[…]\nmpatibility\n\n* feat: Refactor vision engine creation and enhance model path resolution; add face detection tests\n\n* feat: Enhance ONNX benchmark handling and improve result directory labeling in tests",
"is_bot": false,
"headline": "Jm/qbcompiler (#94)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-14T08:52:05Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "aa3e086f762c7ffba5c7afb9bccb5232b9c470dd",
"body": "* feat: Enhance DOTAv1 dataset handling with Google Drive support\n\n- Added functionality to download DOTAv1 image and label archives from a Google Drive folder.\n- Implemented a method to construct the legacy DOTAv1 validation layout from downloaded archives.\n- Updated the dataset configuration to in\n[…]\nfeat: Enhance Google Drive archive handling in organizer with improved URL recognition and error management\n\n* feat: Enhance construct_dotav1_from_archives to preserve existing data on staging failure",
"is_bot": false,
"headline": "feat: Enhance DOTAv1 dataset handling with Google Drive support (#92)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-13T05:03:40Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d430f81c8a12c6ef1a8ac890b25aa9c9f499d6ac",
"body": "…LI (#91)",
"is_bot": false,
"headline": "feat: add --e2e option for YOLO end-to-end postprocessing in vision C…",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-13T01:54:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b55eca3a6c5e6f38e9a470d391fc3d0ae5ec87cb",
"body": "…… (#90)\n\n* feat: add support for nested list tensor types and enhance DFL-free detection/segmentation handling\n\n* test: add DFL-free detection and segmentation tests for batched outputs and reducemax handling\n\n* fix: exclude unused reducemax tensors from proto candidates in DFL-free segmentation",
"is_bot": false,
"headline": "feat: add support for nested list tensor types and enhance DFL-free d…",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-10T04:12:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "210bce8f5bdc33baff720867f77b4864da51c765",
"body": "* fix: trace measured tps runs\n\n* feat: add benchmark trace dir\n\n* fix: auto-detect VLM TPS task\n\n* feat: add per-target qbruntime trace to ASR benchmark\n\nMirrors the text-generation benchmark trace-dir wiring: registers\n--trace-dir on the ASR argument parser and wraps the measured-samples\nloop insi\n[…]\nmeasure. Warmup runs are excluded from the trace.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: TPS 측정 구간 전체 트레이스 수집 (#89)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-07-09T05:59:17Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "32daa1bbc644e174d6e913127e2afcd625449a75",
"body": "* feat: Add support for oriented bounding boxes (OBB) in YOLO models\n\n- Implemented YOLOAnchorlessOBBPost and YOLODFLFreeOBBPost classes for OBB postprocessing.\n- Enhanced results processing to handle OBB outputs, including plotting and evaluation.\n- Updated CLI validation to support OBB models with\n[…]\nenhance OBB support in vision CLI and evaluation scripts\n\n* fix: update DOTA evaluation and test cases for oriented bounding boxes\n\n* feat: add tests for OBB alias in task listing and model resolution",
"is_bot": false,
"headline": "Jm/obb (#88)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-07-08T08:06:40Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "210d13d074d77314f5be07977eeccda106da3836",
"body": "* fix: allow kanana llama config\n\n* fix: validate Kanana llama configs",
"is_bot": false,
"headline": "fix: allow kanana llama config (#87)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-07-07T10:09:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b07f43440a43901bf1d4fdcf167b36a614c4ec0b",
"body": "* fix(tests): skip qwen3-asr cache contract on incompatible qwen-asr/transformers\n\npytest.importorskip(\"qwen_asr\") only catches ImportError, but importing\nqwen_asr triggers a transitive class-body evaluation of its transformers\nbackend that calls @check_model_inputs() in factory form. On the top of\n\n[…]\noth\ntokens and route them to the same `w` bucket.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "Release 2.1.0: transformers version matrix runner + qwen3-asr fix (#86)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-07-04T13:26:12Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "e2ea64e91c250326e0a348dee0e4943640c85347",
"body": "* fix(hf_transformers): propagate NPU kwargs through from_pretrained\n\nAdd missing base_/draft_/fc_ dev_no and max_batch_size setters on\nMobilintEagle3ConfigMixin so those kwargs actually reach the NPU\nbackend instead of being silently dropped by PretrainedConfig.from_dict.\n\nAlso strip text_*/vision_\n[…]\n None for the subconfig core-mode payload fields.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "Fix NPU kwargs propagation and add core-mode fan-out to subconfigs (#85)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-07-04T09:32:52Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "924818a8f3d8db5f070c02ddfd503eb3251b2c31",
"body": "* feat(llm): add HF-style logits_to_keep to shared LLM inference core\n\nThreads `logits_to_keep: Union[int, torch.Tensor] = 1` through\n`llm_forward` and `_llm_forward_batch`, with a 3-way branch:\n\n* logits_to_keep == 1: unchanged fast path (default caller behavior).\n* MXQ with a dynamic token axis (d\n[…]\nvl_model()` needs it alongside `use_return_dict`.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(llm): add HF-style logits_to_keep across LLM/VLM forwards (#84)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-07-04T02:14:02Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "614b156027134e135daedf2f35b9a4b971133def",
"body": "* test: harden CLI compat monkeypatches\n\n* test: pass whisper language via generate_kwargs\n\nThe ASR pipeline on transformers 4.54.1 does not forward unknown\nkwargs to generate, so top-level language=\"en\" raised TypeError.\nWrap it in generate_kwargs so the call works on both 4.54.x and\n>=4.55.\n\nCo-Au\n[…]\nackend detach/reattach and top-level field merge.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>\n\n---------\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "Beomsu/fix pytests (#83)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-07-01T08:40:34Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "575f0eba7f5b9d157240bfea435e21efebd0e809",
"body": "* feat: add model filter\n\n* docs: improve prefill model filter\n\n* fix: require model filter values",
"is_bot": false,
"headline": "Beomsu/update script (#82)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-06-22T08:44:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9879583b5b90b8663223491bfe87cbb29499620d",
"body": "* fix: support tracker 1.0\n\n* test: cover NPU rail metrics CLI\n\n* fix: clarify tracker trace methods\n\n* fix: auto-detect compare task\n\n* feat: add ASR chart rebuild\n\n* fix: normalize compare model keys\n\n* fix: constrain compare owner stripping\n\n* fix: align compare task schema\n\n* refactor: share com\n[…]\nx: avoid partial energy totals\n\n* fix: recreate VLM phase trackers\n\n* docs: fix mblt tracker version\n\n* fix: use current vision energy\n\n* fix: isolate tps phase trackers\n\n* fix: aggregate sweep energy",
"is_bot": false,
"headline": "Improve benchmark tracker energy metrics (#81)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-06-14T03:37:16Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "701defe282fecaa8da94a88df0cc2ebd23b96019",
"body": null,
"is_bot": false,
"headline": "fix: stabilize vision val downloads (#80)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-06-10T08:51:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cda3b7edf257b4c5f3962e2b652efffa1fc16740",
"body": null,
"is_bot": false,
"headline": "fix: guard qwen asr backend",
"author_name": "beomsu",
"author_login": "beomsu-mobilint",
"committed_at": "2026-06-09T08:12:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3ebd0d99d01e90132224f1dddc5043d3de18de51",
"body": "* Make beam search for whisper\n\n* refactor: remove whisper replay code\n\n* Refactor Beam Cache\n\n* Add beam search test\n\n* Fix BeamCache to not use load/dump\n\n* Fix qwen asr for beam cache\n\n* Send core mode to whisper in benchmark script\n\n* chore: add whisper beam tracing\n\n* test: align beam cache tes\n[…]\nts reuse\n\n* fix: isolate whisper cache by source\n\n* fix: group whisper beam sources\n\n* fix: keep whisper embeds path uncached\n\n* fix: isolate Qwen ASR beam cache\n\n* fix: preserve qwen asr beam sources",
"is_bot": false,
"headline": "Add Mobilint ASR beam cache tracing (#78)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-06-09T07:53:33Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "64d7705d3333dc8b11fa85c96bcc3f59fa041894",
"body": "* fix: unify vision model path\n\n* fix: preserve vision path semantics\n\n* fix: preserve legacy local path",
"is_bot": false,
"headline": "fix: unify vision model path (#79)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-06-09T07:19:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5aac8d4ddedaee5a0a731db3a90f0d76ea263cdf",
"body": "* Add initial ASR benchmark\n\n* Fix bugs & set num beams default as none\n\n* Add ASR compare & iterate all dataset\n\n* Remove warning for qwen asr\n\n* Fix legend warning\n\n* fix: improve asr benchmark defaults\n\n* fix: improve ASR benchmark compare\n\n* refactor: share ASR benchmark dataset utils\n\n* fix: re\n[…]\neserve ASR benchmark labels\n\n* fix: support generic ASR retries\n\n* fix: align eagle3 input device\n\n* test: fix eagle3 generate mocks\n\n* test: capture eagle3 warnings\n\n* fix: report effective ASR beams",
"is_bot": false,
"headline": "ASR 벤치마크에 빔 서치 및 정확도 지표 추가 (#77)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-06-08T06:43:59Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "c17e07b9eed4e9d54e616f7646d0045448e4e656",
"body": "* feat: add onnx vision inference\n\n* fix: complete onnx yolo support\n\n* feat: improve ONNX YOLO post-processing with metadata-aware scaling and robust tests\n\n* docs: update vision CLI guide with aliases and ONNX support\n\n* fix: make onnxruntime optional\n\n* fix: improve onnx compatibility and platfor\n[…]\npecific install guides\n\n* fix: robustly handle YOLO outputs and ONNX input layout normalization\n\n* feat: allow configuring ONNX Runtime execution providers\n\n* docs: expand ONNX support scope in README",
"is_bot": false,
"headline": "Jm/onnx (#76)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-06-08T01:56:32Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "acebec3e60c4a999d92a2ce6644dcde6a68a7469",
"body": null,
"is_bot": false,
"headline": "docs: add vision CLI guide (#75)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-06-05T03:56:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6c28ddabcba24e36c1888ca35a227fe77ea43efd",
"body": "* fix: restore vision import compatibility\n\n* fix: decouple core mode helpers",
"is_bot": false,
"headline": "fix: restore vision import compatibility (#74)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-06-04T00:57:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8f0a7b0c41ee8da724e022082e56c696cca065c1",
"body": "* refactor: migrate vision model definitions to YAML configuration files and remove legacy Python implementations\n\n* chore: migrate PyPI publishing to OIDC authentication and update Node runtime environment\n\n* temp update\n\n* refactor: align vision benchmark args\n\n* fix: tighten yolo postprocess typi\n[…]\nlds\n\n* feat: add yolo post overrides\n\n* refactor: unify yolo decode paths\n\n* fix: harden vision yaml migration\n\n* fix: restore DeiT and YOLO registry\n\n* fix: expose shufflenet x0 5\n\n* hotfix\n\n* hotrix",
"is_bot": false,
"headline": "Jm/yaml (#73)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-06-02T09:08:07Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "bf60dc00e8baf876361b101d66d57659996110a1",
"body": "* Implement EAGLE3\n\n* Refactor qwen2 eagle3\n\n* Refactor pytests\n\n* Fix qwen2 eagle3 generate\n\n* Remove dummy param\n\n* Fix multi-turn conversation for EAGLE3\n\n* Make stopping criteria work for EAGLE3 and add `count_npu_time`\n\n* Refactor EAGLE3\n\n* test: stabilize eagle3 cache and tps tests\n\n* Refactor\n[…]\nopts\n\n* docs: clarify eagle3 draft model\n\n* fix: support eagle3 core mode sweep\n\n* Fix pytest\n\n* Divide Qwen3 VL tests\n\n* fix: support eagle3 rope on tf520\n\n* fix: guard aya vision decode image inputs",
"is_bot": false,
"headline": "Beomsu/eagle3 (#72)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-06-01T08:29:02Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "6312c5d16b5ae2a8c64bfb4bd03f1a275782fb5a",
"body": "* Add Qwen3-VL-8B-Instruct\n\n* Fix wrappers\n\n* Fix VLM tps cli\n\n* Add MobilintDeepStackCache\n\n* Fix loop\n\n* Add fake prefill as result\n\n* Refactor benchmark scripts\n\n* Update README.md\n\n* feat: align transformer benchmarks\n\n* Update `mblt-tracker`\n\n* Add assert for num_of_chunks\n\n* Fix cli help sente\n[…]\n batched decode metrics\n\n* fix: write VLM TPS sweep plot\n\n* fix: preserve sweep durations\n\n* fix: set matplotlib backend early\n\n* fix: honor VLM measure prefill\n\n* Fix qwen3 tests\n\n* Remove python 3.9",
"is_bot": false,
"headline": "Beomsu/update benchmark (#71)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-05-26T03:48:16Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "7443444176a7b365df37327a613cfd695339d6e5",
"body": "`Transformers` sets `config.name_or_path = pretrained_model_name_or_path`\nonly after `from_dict` returns and right before `cls(config, ...)`. The\nexisting explicit propagation inside `MobilintVisionTextConfigMixin.from_dict`\nruns too early, so sub-configs end up with an empty `name_or_path`.\n\nWhen `\n[…]\ntches the assignment in\n`PreTrainedModel.from_pretrained` and keeps sub-configs in sync for any\nfuture vision-text Mobilint model.\n\nCo-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>",
"is_bot": false,
"headline": "Propagate parent name_or_path to vision_config and text_config (#70)",
"author_name": "Jiwook Hwang",
"author_login": "phypan11",
"committed_at": "2026-05-19T02:15:57Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "1f0f9157677b23348faf70494dc863286559a7bf",
"body": "Add: HF ASR pipeline support and pytest for Qwen3-ASR",
"is_bot": false,
"headline": "Merge pull request #69 from mobilint/khh/fix-qwen3-asr",
"author_name": "khh0303",
"author_login": "khh0303",
"committed_at": "2026-05-12T02:21:47Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6618a3f45518d22a8dc5f57054914f1a088b54b2",
"body": null,
"is_bot": false,
"headline": "Add: include Qwen3-ASR-0.6B in pytest model sweep",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-12T02:20:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ec39605c399d0a0479f08cd3988f2673d9c7b528",
"body": "Guard against the case where super().generate() returns a plain tensor\n(standard transformers behaviour when return_dict_in_generate=False).\nToday upstream Qwen3-ASR hard-codes return_dict_in_generate=True so this\npath is unreachable, but the defensive branch keeps prefix stripping\ncorrect if upstream switches to the standard convention.",
"is_bot": false,
"headline": "Add: tensor branch in pipeline generate path for prefix stripping",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-11T02:01:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8a1f5b65d9965728b67016ec7746ecbb2cd29402",
"body": null,
"is_bot": false,
"headline": "Add: pytest covering Qwen3-ASR HF pipeline and transcribe paths",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-11T01:40:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "03f67cb23979fe11824d4b6b45170f7e9b6b6ca1",
"body": "Route encoder_*/decoder_* kwargs to the nested audio/text NPU backends and\nregister the model in MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING_NAMES so\ntransformers.pipeline('automatic-speech-recognition') exercises the\ngenerative path. Add a generate() override that synthesises the chat\ntemplate prompt and strips the language prefix when only audio is given.",
"is_bot": false,
"headline": "Add: HF ASR pipeline support for Qwen3-ASR",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-11T01:40:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f36ff293c65c76b712bb3ba2e4e05a6dd8e5be71",
"body": null,
"is_bot": false,
"headline": "Chore: ignore venv directory",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-11T01:40:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "08455578556b8b5ef90dd439b9d2612df1ede2fa",
"body": null,
"is_bot": false,
"headline": "Update: version 1.5.1",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-10T05:48:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3db14f293b6c34bb4a608b3493e63b3c8ffea776",
"body": "기존 MobilintQwen3ASRTextModel 은 ASR text MXQ 가 3D `(1, S, hidden)`\n입력으로 컴파일되었기 때문에 부모 MobilintModelMixin.llm_forward\n(4D `(1, 1, S, hidden)` + BatchParam 가정) 를 못 쓰고 자체 3D 전용\n_llm_forward 를 유지해야 했다.\n\nqbcompiler 파서에서 set_attention_mask 패턴을 적용해 ASR text MXQ 도\n다른 LLM 들과 동일한 4D NHWC layout 으로 컴파일되었기 때문에 자체\n_llm_forward 가 더 이상 필요 없다. 부모 llm_forward 를 호출하도록\n교체하고 (attention_mask=None 으로 단일 batch path 사용), 56줄짜리\noverride 메서드와 import time 을 제거한다.",
"is_bot": false,
"headline": "Update: ASR text model uses parent llm_forward for 4D MXQ",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-08T10:11:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9fd0978bf737a29c1e658b3f42be22749ceb8b42",
"body": null,
"is_bot": false,
"headline": "Bump version to 1.5.0",
"author_name": "khh0303",
"author_login": "khh0303",
"committed_at": "2026-05-08T04:48:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7ccc1ab1c7079d7cd429b45ab4b979729a263690",
"body": "Add: Mobilint Qwen3-ASR integration for NPU inference",
"is_bot": false,
"headline": "Merge pull request #68 from mobilint/khh/qwen3-asr",
"author_name": "khh0303",
"author_login": "khh0303",
"committed_at": "2026-05-08T04:29:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "011fb9ac0a96ecdff2640b0b3633d8f2f72b9bc2",
"body": "The audio encoder zero-pads the final mel chunk to 100 frames and\nconcatenates the encoder's full 13-token output. When feature_lens is\nnot an exact multiple of 100, this emits more audio embeddings than the\nprocessor's audio_token_id placeholders allocated in the prompt: the\nupstream Qwen3-ASR form\n[…]\nract_output_lengths tail term (three stride-2\nconv stages applied to tail_frames). Mid-stream chunks remain at 13\ntokens, so the fixed-length fast path still holds for everything except\nthe EOS chunk.",
"is_bot": false,
"headline": "Fix: drop padded tail audio tokens to match placeholder count",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-08T03:59:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "36859b9f84b5a64d18ff0b62fbbe835178e01048",
"body": "Mobilint Qwen3-ASR wrappers hard-import the external qwen-asr package,\nwhich is not bundled with the mblt_model_zoo[transformers] extra. Until\nthat package is installed, users hit a bare ModuleNotFoundError that\ngives no recovery hint, and proxy_qwen3_asr.py made it worse by\nsuggesting \"pip install \n[…]\nstall -U qwen-asr\" instruction. Tighten the proxy's\nfallback to only rewrite when mblt_model_zoo itself is missing, so the\nwrapper's actionable message propagates through trust_remote_code load\npaths.",
"is_bot": false,
"headline": "Update: guide users to install qwen-asr on missing-import error",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-08T03:34:39Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2f190b8c415c09e7742969ed932db935d0d076ea",
"body": null,
"is_bot": false,
"headline": "Chore: ignore .omc working directory",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-07T00:40:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "edd3ab4f8aaef255f866c9a3be13f0bb06497ea0",
"body": "config / modeling / processing / proxy 5 파일 추가. 원본\nqwen_asr Qwen3ASRForConditionalGeneration 위에 Mobilint NPU\nsubclass 를 얹어 audio encoder (100-frame mel chunk) 와 text\ndecoder (chunked prefill + AR decode) 를 MXQ 로 처리한다.\nAutoModel / AutoModelForSpeechSeq2Seq register 포함.",
"is_bot": false,
"headline": "Add: Mobilint Qwen3-ASR integration for NPU inference",
"author_name": "hyunghoon",
"author_login": "khh0303",
"committed_at": "2026-05-06T10:32:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f5aed0279766f6708f65937390d9d8aba848e63d",
"body": "* Skip Qwen3 VL tests when transformers version is low\n\n* Fix test_cache.py\n\n* Fix Qwen VL nested config with transformers 5.0.0~5.3.0\n\n* Update proxy_whisper.py\n\n* Fix aya vision config\n\n* Fix Cohere2 Config with use_cache type\n\n* Update transformers version\n\n* Update fix version\n\n* Fix prepare_inp\n[…]\n the case of cache_position only input\n\n* Refactor whisper feature extractor name\n\n* Move test files into appropriate directories\n\n* Add whisper models in pytest\n\n* Rename test folders in transformers",
"is_bot": false,
"headline": "Skip Qwen3-VL tests for lower versions of `transformers` (#67)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-27T03:45:34Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "e42cd18271cd0147534ce90940aa4be4052b616f",
"body": "* Add trust_remote_code for auto classes\n\n* Add --full-matrix option for pytests\n\n* Set return_dict=False for tests\n\n* Add PretrainedOnlyMixin for WhisperForConditionalGeneration\n\n* Change deprecated attribute `use_return_dict` to `return_dict`\n\n* Set max new tokens to 32 when --full-matrix is not e\n[…]\nnt for batch/non-batch tests\n\n* Add transformers version warning for Qwen3 VL\n\n* Update fix version\n\n* Fix pytest to enable explicit model id selection eg. test_qwen3_vl[mobilint/Qwen3-VL-8B-Instruct]",
"is_bot": false,
"headline": "Refactor pytests for short sanity tests (#66)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-23T09:05:41Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "2494b50174646a447611fd74235c3de0253c1d8a",
"body": "* Update transformers to 5.0.0\n\n* Fix ruff check\n\n* Make cli compatible before/after transformers==5.0.0\n\n* Fix import error for SpecificPretrainedConfig\n\n* Fix transformers cli compatibility\n\n* Add regression tests for cli\n\n* Call transformers serve hook only when needed",
"is_bot": false,
"headline": "Supports transformers>=5.0.0 (#65)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-22T01:05:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5298c9f852c7a4a15aff3066acb9039e60a5ee82",
"body": null,
"is_bot": false,
"headline": "Opt codex review into unsandboxed fallback",
"author_name": "jinman",
"author_login": "parkjinman98",
"committed_at": "2026-04-21T05:03:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "91bf78136a625a63b1aecfae47e3fe7ae7043019",
"body": "* Refactor tests for text-generation models\n\n* Fix batch test for core sweep\n\n* fix: reuse base npu params in batch\n\n* Update AGENTS.md\n\n* Fix import error\n\n* Fix function name\n\n* Fix batch tests with core sweep",
"is_bot": false,
"headline": "Refactor tests for text-generation models (#64)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-21T05:00:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "39a05af14e279f32748458804eb5f909025db6e2",
"body": null,
"is_bot": false,
"headline": "feat: add pull_request_review event to workflow triggers",
"author_name": "jinman",
"author_login": "parkjinman98",
"committed_at": "2026-04-20T09:02:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4a84081d5978547a660eccf85a4256dda491fc9b",
"body": null,
"is_bot": false,
"headline": "Add conditional check for issue comments in workflow (#63)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-04-20T08:46:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1f697be5348cd4902ac6bf832f1f7d6e8dfb99e5",
"body": null,
"is_bot": false,
"headline": "fix: restore codex review write scopes (#62)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-04-20T07:35:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a276e54ae471652a26d5b201932d38651c7d914b",
"body": null,
"is_bot": false,
"headline": "Bump version to 1.3.1",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-04-20T01:26:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "57a0ea882f3faca0b15997d489b106bd90433d00",
"body": null,
"is_bot": false,
"headline": "Fix return type in Normalize class to ensure output is always float32",
"author_name": "jinman",
"author_login": "parkjinman98",
"committed_at": "2026-04-20T01:22:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4174a1beb2e83fd8298c17fadfea5164f751f4bc",
"body": "* Replace device trackers\n\n* Add temperature",
"is_bot": false,
"headline": "Use mblt-tracker (#60)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-20T00:34:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d8ad10b826b7712f63ea91ed44ade60b57dd9cc4",
"body": null,
"is_bot": false,
"headline": "Add Codex Review workflow for pull requests",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-04-15T05:06:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bbd98bfa214efa1a94d3b4dad2e46ebf1737ddf1",
"body": "* Add test_llama_batch\n\n* Add BatchTextStreamer\n\n* Update mobilint-qb-runtime to 1.2.0\n\n* Fix test fixtures\n\n* Update version",
"is_bot": false,
"headline": "Add batch inference LLM for Llama (#59)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-10T01:15:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "247002c76b4a51fc729b170e407c63d7ba4a3ed0",
"body": "* - docs: add repo agent guidance and skill\n - fix: correct vision mask encoding and Aries core mode\n\n* chore: bump version to 1.2.2",
"is_bot": false,
"headline": "Jm/hotfix (#58)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-04-07T02:21:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a4dea9006906da7f82ff7dd45c60d11486fc12f8",
"body": null,
"is_bot": false,
"headline": "Update version (#57)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-05T00:33:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cdeba37d6abff07bc2f56f7b4941ddb987ab2292",
"body": null,
"is_bot": false,
"headline": "Fix prefill chunk size name conflict (#56)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-05T00:32:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6187f2ab82c83e1fc02c05a22085fc2c93d7ce87",
"body": "* Add qwen3_vl\n\n* Fix qwen2 vl\n\n* Update version\n\n* Update publish.yml",
"is_bot": false,
"headline": "Add qwen3_vl (#55)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-03T08:57:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7becee3220a94e78d70c1243f67c1992bc352cb3",
"body": "…yPI configuration",
"is_bot": false,
"headline": "ci: add TestPyPI publication step and update build dependencies and P…",
"author_name": "jinman",
"author_login": "parkjinman98",
"committed_at": "2026-04-03T04:24:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "24b4914d565412af173875b6bc0d301c890c21a6",
"body": "* Support all core modes in benchmarks, pytest, and docs\n\n* Fix benchmark for original models\n\n* Narrow down search area for chunk size search\n\n* Fix search script to run without mxq dir path\n\n* Update prefill_chunk_size.csv\n\n* Rename chunk_size to prefill_chunk_size and apply best chunk sizes to config.json\n\n* Fix how tps measure works for LLMs\n\n* Fix how tps measure works for VLMs",
"is_bot": false,
"headline": "Apply all core modes for LLMs (#54)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-04-03T03:56:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d0b42b39d41b47894bcd388e706d07134aa4fce8",
"body": "…in the package namespace (#53)",
"is_bot": false,
"headline": "refactor: update YOLO pose model to 11x and export all vision models …",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-04-01T07:04:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "54e01a242ff17ddfc1dc5644dc97ac3dd8ba003e",
"body": "* feat: Introduce CLI tools for classification, detection, segmentation, and pose estimation, standardize model preprocessing with normalization, and refactor model configurations using OrderedDict.\n\n* refactor: Use direct method `get_model_input_data_type` for retrieving model input data type.\n\n* r\n[…]\nE model metrics.\n\n* refactor: apply automatic code formatting and remove unused imports across the codebase\n\n* chore: bump version to 1.1.0, add linting ignores, and update VGG model metrics in README",
"is_bot": false,
"headline": "Jm/result (#52)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-04-01T04:05:03Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "16f602b7bbe14ba7bc8f8356b7250a8f620e737d",
"body": "* Expand the benchmarking and comparison tooling with new CLI options, chunk-size tuning, and support for original models and vision benchmark comparisons.\n\n* Add power, energy, utilization, and memory metrics, CUDA memory checks, and progress reporting with tqdm.\n\n* Refactor charts, common CLI utilities, and benchmark/search workflows, along with bug fixes, import path cleanup, auto device selection, and README updates.",
"is_bot": false,
"headline": "Beomsu/update benchmark (#51)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-03-25T06:09:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "22d44e5ec91e8eca4791f20ba15e9190c643a1ce",
"body": null,
"is_bot": false,
"headline": "fix #47 (#50)",
"author_name": "hong-mobilint",
"author_login": "hong-mobilint",
"committed_at": "2026-03-12T06:08:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fc06eec25e252227e0b5794fed3814befe8ff6a8",
"body": "* Fix TTS cuda device error\n\n* Add build package as dev dependency",
"is_bot": false,
"headline": "Beomsu/tts error (#49)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-03-09T07:42:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "34cce2ac6ea1dc3c07eee8da113815c2b099dc17",
"body": "* Add VLM tps measurement\n\n* Add power tracker\n\n* Measure power efficiencyt\n\n* Update dependency\n\n* Update tps vlm-sweep\n\n* Update tps.py to show stack trace\n\n* Fix power tracker lifecycle\n\n* Fix VLM feature dimension\n\n* Fix VLM feature dimension\n\n* Fix count_npu_time when GPU\n\n* Remove DFI\n\n* Use total power consumption with npu\n\n* Add power data for vision encoder with VLM\n\n* Add tqdm\n\n* Show power consumption for tps measure\n\n* Add power info for vlm sweep\n\n* Fix tqdm",
"is_bot": false,
"headline": "Beomsu/vlm benchmark (#48)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-03-04T09:21:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "56b6b7cde83494e9b708eb4049875b2b53ea0725",
"body": "* refactor: Rename `YoloPre` to `LetterBox` in preprocessing configurations\n\n* feat: Add Ray Tune for YOLO model compilation hyperparameter tuning, correct keypoint permutation in DFL-free post-processing, and remove unused anchorless post-processing filter conversion.\n\n* feat: Standardize model con\n[…]\nants across vision tasks.\n\n* feat: Add YOLOv8xPoseP6 model\n\n* feat: Add multiple new image classification models\n\n* hotfix\n\n* googlenet, inception with modification\n\n* minor fix\n\n* hotfix\n\n* minor fix",
"is_bot": false,
"headline": "Jm/bench (#46)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-02-27T09:17:05Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ed2ad3546283d47b9882cdf013819de8dc93f985",
"body": "* Fix dependency issue for Windows with g2pkk\n\n* Filter DepecationWarning\n\n* Fix union type for python 3.9",
"is_bot": false,
"headline": "Beomsu/compatibilities (#45)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-02-18T13:46:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ddebe3eb8d9f099254d6e4ed461f056e3d397dfa",
"body": "* initiali commit\n\n* normalize removed\n\n* hotfix\n\n* feat: Add YOLO26 models for detection, segmentation, and pose estimation, and introduce a face detection module.\n\n* Refactor post-processing configurations by removing explicit detection layer count and simplifying anchor definitions to a boolean f\n[…]\nOCO benchmarking script.\n\n* temp update\n\n* python version change\n\n* refactor: Update type hints for image inputs to `np.ndarray` and standardize optional list/tuple parameters using `typing.Optional`.",
"is_bot": false,
"headline": "Jm/v1.0.0 (#41)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-02-12T01:51:08Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "33ad1830870b77dd31868d1a40eabbfce364a5b4",
"body": null,
"is_bot": false,
"headline": "Add no_launch keyward argument (#44)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-02-11T03:07:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c75689725bf4c5c69537446c8fe9f1c5976a2adc",
"body": "* Update text-generation benchmark to test all revisions\n\n* Fix bug about revision kwarg\n\n* Add NPU time measurement\n\n* Add NPU time percentage for benchmark result",
"is_bot": false,
"headline": "Beomsu/benchmark update (#43)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-02-10T07:47:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2483a0331c12f251a1f9f2c81e212bef242f884c",
"body": "* Add melotts download\n\n* Add eunjeon for Windows dependency\n\n* Fix test_cache to reuse past_key_values\n\n* Fix small models misunderstand prompt for cache testing",
"is_bot": false,
"headline": "Beomsu/melo download fix (#42)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-02-10T07:39:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4587cb27f69e6a3507a09e2a3118d8124f0f3354",
"body": null,
"is_bot": false,
"headline": "Rename qbruntime to mobilint-qb-runtime in dependencies",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2026-02-03T06:17:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "447b92f845289439d6687d691e8bd74aa464cc0b",
"body": null,
"is_bot": false,
"headline": "Fix input order of blip text model (#40)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-01-30T06:54:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e007b2afae7e8e9652084a6591e003a3131b39da",
"body": "* Update README.md\n\n* Add test_melo.py\n\n* Add TEST.md in MeloTTS\n\n* Move MobilintNPUBackend to higher utils\n\n* Add unidic download script\n\n* Remove reset_cache_memory\n\n* Add model variants on log_model_details\n\n* Make melo_app cli\n\n* Remove noisereduce\n\n* Add local_files_only and trust_remote_code\n\n* Make trust_remote_code, local_files_only work for bert\n\n* Add main.py for MeloTTS\n\n* Add missing dependency for chat cli\n\n* Add chat helper\n\n* Add benchmark results in .gitignore",
"is_bot": false,
"headline": "Add MeloTTS models (#39)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-01-30T02:26:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "46f05525fbe6bc6982ffda48d22186b588c15143",
"body": null,
"is_bot": false,
"headline": "Fix cli bugs (#38)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-01-28T10:58:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f34ab4e15c68b797aa18af1082e740f522ca80bc",
"body": "* Make common code into Mixin classes\n\n* Reflect original code as many as possible\n\n* Add customizable keyword parameters for easy testing\n\n* Rework how list_models() work\n\n* Upload models on HuggingFace Hub",
"is_bot": false,
"headline": "Refactor `transformers` codes (#37)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2026-01-28T09:05:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c8af06bfd060abafd960aedad8f6c25b67a059cc",
"body": "raise when download fail to prevent fallback to transformers",
"is_bot": false,
"headline": "Merge pull request #35 from mobilint/beomsun/develop",
"author_name": "hong-mobilint",
"author_login": "hong-mobilint",
"committed_at": "2025-12-02T08:58:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "14777ea16e425e869187f56bb07a7c557aec5056",
"body": null,
"is_bot": false,
"headline": "raise when download fail to prevent fallback to transformers",
"author_name": "Beomsun Hong",
"author_login": "hong-mobilint",
"committed_at": "2025-12-02T08:42:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "18da3232450ef7030e6f9f347f96d89f3aff9347",
"body": "* minor patch\n\n* test revision\n\n* minor fix\n\n* test style fix",
"is_bot": false,
"headline": "Jm/patch (#34)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2025-11-27T01:49:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "97918b946088d038cf7068be5cd0d29f876cc69b",
"body": null,
"is_bot": false,
"headline": "Bump version to 0.4.3",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2025-11-25T05:25:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "194eb6feebcda106a1c3c2cf6eacf1dd283e4fc7",
"body": null,
"is_bot": false,
"headline": "regulus tag (#33)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2025-11-25T05:23:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e7fad91a499fabbf557f55eb7d059039ab5863bd",
"body": "* Fix initializing package without transformers\n\n* Update version\n\n* Fix vision tests to use relative path",
"is_bot": false,
"headline": "Beomsu/fix transformers dependency (#32)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2025-11-20T08:53:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5145e080bd1cf9f334edb1e4a7edbc2eec8a912c",
"body": "* misc update\n\n* Run pre-commit\n\n---------\n\nCo-authored-by: beomsu <beomsu@mobilint.com>",
"is_bot": false,
"headline": "misc update (#31)",
"author_name": "Jinman Park",
"author_login": "parkjinman98",
"committed_at": "2025-11-20T06:44:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "69c8eb2908f96d648873beb0e4fb493975464d4f",
"body": null,
"is_bot": false,
"headline": "Release 0.4.1",
"author_name": "beomsu",
"author_login": "beomsu-mobilint",
"committed_at": "2025-11-20T05:39:31Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9a8ce76a60a509fe95356e40b9125a1780d112a7",
"body": null,
"is_bot": false,
"headline": "Fix cache reset (#30)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2025-11-20T05:32:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ee18af57c58366c441a5c4b362a0760b0ad6a029",
"body": "* Fix wrong type for list_models\n\n* Add overloads for pipeline\n\n* Remove unused imports\n\n* Change get_mxq_model to get_cache_mxq_model",
"is_bot": false,
"headline": "Fix wrong typing in codes (#29)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2025-11-20T05:23:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0e3aa9d5a276e53250b8370fa446d7a49ba47105",
"body": "* Add uv related files to .gitignore\n\n* Add new models\n\n* Add tests for various model paths\n\n* Organize test files\n\n* Update dependencies\n\n* Fix download failed message\n\n* Change path to os.path.join\n\n* Add log_model_details\n\n* Update README.md\n\n* Update TEST.md\n\n* Add mxq_path fixture for AutoModelForCausalLM tests\n\n* Reset cache when theres no cache in pipeline\n\n* Add timeout for exaone deep test\n\n* Change model config for whisper encoder",
"is_bot": false,
"headline": "Add new LLM models (#28)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2025-11-20T05:13:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8003d9aaf736fd76ab72b3889f1f996dd62b4ff5",
"body": null,
"is_bot": false,
"headline": "Update README.md for transformers (#27)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2025-11-10T08:36:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8413871d5b84618dd6f7f1f239b2d1d84bf438d7",
"body": "* Add qwen2.py\n\n* Update version to 0.4.0",
"is_bot": false,
"headline": "Add Qwen2.5-7B-Instruct (#26)",
"author_name": "beomsu-mobilint",
"author_login": "beomsu-mobilint",
"committed_at": "2025-11-10T08:18:24Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 30,
"commits_last_year": 118,
"latest_release_at": "2026-08-01T04:42:21Z",
"latest_release_tag": "v2.3.0",
"releases_from_tags": false,
"days_since_last_push": 0,
"active_weeks_last_year": 38,
"days_since_latest_release": 0,
"mean_days_between_releases": 11.1
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": true,
"has_contributing": false,
"health_percentage": 50,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "mblt-model-zoo",
"exists": true,
"license": "BSD-3-Clause",
"keywords": [
"quantization",
"NPU",
"model zoo",
"pre-quantized models",
"inference",
"mobilint",
"mblt",
"aries",
"regulus",
"qb",
"Development Status :: 4 - Beta",
"Environment :: Console",
"Intended Audience :: Developers",
"Intended Audience :: Education",
"Intended Audience :: Science/Research",
"Intended Audience :: System Administrators",
"License :: OSI Approved :: BSD License",
"Operating System :: Microsoft :: Windows",
"Operating System :: POSIX :: Linux",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Topic :: Scientific/Engineering",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Software Development",
"Topic :: Software Development :: Libraries",
"Topic :: Software Development :: Libraries :: Python Modules"
],
"ecosystem": "pypi",
"matches_repo": true,
"registry_url": "https://pypi.org/project/mblt-model-zoo/",
"is_deprecated": false,
"latest_version": "2.3.0",
"repository_url": "https://github.com/mobilint/mblt-model-zoo",
"versions_count": 31,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": null,
"first_published_at": "2025-04-09T09:14:42.730005Z",
"latest_published_at": "2026-08-01T04:43:28.781092Z",
"latest_version_yanked": null,
"days_since_latest_publish": 0
}
]
},
"popularity": {
"forks": 1,
"stars": 23,
"watchers": 2,
"fork_history": {
"days": [
{
"date": "2026-05-23",
"count": 1
}
],
"complete": true,
"collected": 1,
"total_forks": 1
},
"star_history": null,
"open_issues_and_prs": 1
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [],
"has_llms_txt": false,
"has_dockerfile": false,
"has_mcp_signal": false,
"bootstrap_files": [],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [],
"toolchain_manifests": [],
"largest_source_bytes": 167903,
"source_files_sampled": 352,
"oversized_source_files": 11,
"agent_instruction_files": [
"AGENTS.md",
"CLAUDE.md"
],
"agent_instruction_max_bytes": 15421
},
"dependencies": {
"manifests": [
"pyproject.toml"
],
"advisories": {
"error": "No resolved dependencies carried a version and a supported ecosystem",
"scope": "repository_graph",
"source": null,
"findings": [],
"collected": false,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 0,
"malicious_count": 0,
"assessed_package": null,
"unassessed_count": 23,
"direct_affected_count": 0
},
"ecosystems": [
"pypi"
],
"dependencies": [
{
"name": "mobilint-qb-runtime",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=1.2.0"
},
{
"name": "numpy",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=1.26.0"
},
{
"name": "torch",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=2.4.1"
},
{
"name": "opencv-python",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=4.11.0.86"
},
{
"name": "pillow",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=11.1.0"
},
{
"name": "faster-coco-eval",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "huggingface-hub",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "scipy",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "requests",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=2.32.0"
},
{
"name": "gdown",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=5.2.0"
},
{
"name": "tqdm",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "mblt-tracker",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=1.0.1"
},
{
"name": "PyYAML",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "matplotlib",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
},
{
"name": "cityscapesScripts",
"manifest": "pyproject.toml",
"ecosystem": "pypi",
"version_constraint": null
}
],
"all_dependencies": {
"error": null,
"source": "github-sbom",
"packages": [
{
"name": "gdown",
"direct": true,
"version": null,
"ecosystem": "pypi"
},
{
"name": "mblt-tracker",
"direct": true,
"version": null,
"ecosystem": "pypi"
},
{
"name": "mobilint-qb-runtime",
"direct": true,
"version": null,
"ecosystem": "pypi"
},
{
"name": "numpy",
"direct": true,
"version": null,
"ecosystem": "pypi"
},
{
"name": "opencv-python",
"direct": true,
"version": null,
"ecosystem": "pypi"
},
{
"name": "pillow",
"direct": true,
"version": null,
"ecosystem": "pypi"
},
{
"name": "requests",
"direct": true,
"version": null,
"ecosystem": "pypi"
},
{
"name": "torch",
"direct": true,
"version": null,
"ecosystem": "pypi"
},
{
"name": "anyascii",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "datasets",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "g2p-en",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "g2pkk",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "jamo",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "jiwer",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "librosa",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "numba",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "pre-commit",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "pytest",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "python-mecab-ko",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "qbcompiler",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "setuptools",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "transformers",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "unidic",
"direct": false,
"version": null,
"ecosystem": "pypi"
}
],
"collected": true,
"truncated": false,
"total_count": 23,
"direct_count": 8,
"indirect_count": 15
}
},
"maintainership": {
"issues": {
"open_prs": 1,
"merged_prs": 99,
"open_issues": 0,
"closed_ratio": 1,
"closed_issues": 1,
"closed_unmerged_prs": 2
},
"bus_factor": 2,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "beomsu-mobilint",
"commits": 54,
"avatar_url": "https://avatars.githubusercontent.com/u/205577356?v=4"
},
{
"type": "User",
"login": "parkjinman98",
"commits": 51,
"avatar_url": "https://avatars.githubusercontent.com/u/67285913?v=4"
},
{
"type": "User",
"login": "khh0303",
"commits": 14,
"avatar_url": "https://avatars.githubusercontent.com/u/265239012?v=4"
},
{
"type": "User",
"login": "Sunghoon-mobilint",
"commits": 3,
"avatar_url": "https://avatars.githubusercontent.com/u/265192640?v=4"
},
{
"type": "User",
"login": "hong-mobilint",
"commits": 3,
"avatar_url": "https://avatars.githubusercontent.com/u/229276031?v=4"
},
{
"type": "User",
"login": "parroteffect",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/65681621?v=4"
},
{
"type": "User",
"login": "phypan11",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/6318995?v=4"
},
{
"type": "User",
"login": "keg9335",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/53503771?v=4"
}
],
"contributors_sampled": 8,
"top_contributor_share": 0.422
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"code-review.yml",
"publish.yml"
],
"has_docs_dir": false,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": true
},
"security_signals": {
"lockfiles": [],
"scorecard": {
"checks": [
{
"name": "Binary-Artifacts",
"score": 10,
"reason": "no binaries found in the repo",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
},
{
"name": "Branch-Protection",
"score": null,
"reason": "internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 2,
"reason": "7 out of 26 merged PRs checked by a CI test -- score normalized to 2",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
},
{
"name": "CII-Best-Practices",
"score": 0,
"reason": "no effort to earn an OpenSSF best practices badge detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
},
{
"name": "Code-Review",
"score": 1,
"reason": "Found 4/30 approved changesets -- score normalized to 1",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 0,
"reason": "project has 0 contributing companies or organizations -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": 10,
"reason": "no dangerous workflow patterns detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
},
{
"name": "Dependency-Update-Tool",
"score": 0,
"reason": "no update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 0,
"reason": "project is not fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 10,
"reason": "license file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 10,
"reason": "30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
},
{
"name": "Packaging",
"score": 10,
"reason": "packaging workflow detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": 0,
"reason": "dependency not pinned by hash detected -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 0,
"reason": "SAST tool is not run on all commits -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 0,
"reason": "security policy file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": null,
"reason": "no releases found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
},
{
"name": "Token-Permissions",
"score": 9,
"reason": "detected GitHub workflow tokens with excessive permissions",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 10,
"reason": "0 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "a94608be561e3e076eb03ee2545547aa3145f66d",
"ran_at": "2026-08-01T04:47:44Z",
"aggregate_score": 5.3,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-08-01T04:43:32Z",
"oldest_open_prs": [
{
"number": 103,
"created_at": "2026-07-31T00:50:34Z",
"last_comment_at": "2026-07-31T01:32:18Z",
"last_comment_author": "parkjinman98"
}
],
"last_merged_pr_at": "2026-08-01T04:40:28Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": []
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/mobilint/mblt-model-zoo",
"host": "github.com",
"name": "mblt-model-zoo",
"owner": "mobilint"
},
"metrics": {
"overall": {
"key": "overall",
"band": "excellent",
"name": "Overall health",
"note": "The weighted overall 68 is calibrated to 80 on the published index scale (record calibration 2026-08-02).",
"notes": [
{
"code": "overall_calibration",
"params": {
"raw": 68,
"calibrated": 80,
"calibration": "2026-08-02"
}
}
],
"value": 80,
"inputs": {
"security": 53,
"vitality": 94,
"community": 35,
"governance": 71,
"calibration": "2026-08-02",
"engineering": 77,
"ai_readiness": 60,
"weighted_overall_raw": 68
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "exceptional",
"name": "Vitality",
"value": 94,
"weight": 0.21,
"metrics": [
{
"key": "development_activity",
"band": "excellent",
"name": "Development activity",
"note": null,
"notes": [],
"value": 90,
"inputs": {
"commits_last_year": 118,
"human_commit_share": 1,
"days_since_last_push": 0,
"active_weeks_last_year": 38
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 0 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 0
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "38/52 weeks with commits",
"points": 26.3,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 38
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "118 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 118
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "exceptional",
"name": "Release discipline",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 100,
"inputs": {
"releases_count": 30,
"latest_release_tag": "v2.3.0",
"releases_from_tags": false,
"days_since_latest_release": 0,
"mean_days_between_releases": 11.1
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "30 releases published",
"points": 27,
"status": "met",
"details": [
{
"code": "releases_published",
"params": {
"count": 30
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 0 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 0
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~11.1 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 11.1
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "exceptional",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "maintained",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": null,
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": 1,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "last human commit 1 days ago",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_maintained",
"params": {
"days": 1
}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "weak",
"name": "Community & Adoption",
"value": 35,
"weight": 0.17,
"metrics": [
{
"key": "popularity",
"band": "at_risk",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 22,
"inputs": {
"forks": 1,
"stars": 23,
"watchers": 2,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "23 stars",
"points": 21.8,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 23
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "1 forks",
"points": 0,
"status": "missed",
"details": [
{
"code": "forks",
"params": {
"count": 1
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "2 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 2
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "moderate",
"name": "Community health",
"note": null,
"notes": [],
"value": 50,
"inputs": {
"has_readme": true,
"has_license": true,
"readme_badges": null,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"readme_badge_services": [],
"has_pull_request_template": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "recognized license (BSD-3-Clause)",
"points": 22.5,
"status": "met",
"details": [
{
"code": "license_standard",
"params": {}
},
{
"code": "license_spdx",
"params": {
"spdx": "BSD-3-Clause"
}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "code_of_conduct",
"name": "Code of conduct",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 13.5
},
{
"key": "issue_template",
"name": "Issue template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.2
},
{
"key": "pr_template",
"name": "PR template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.3
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "good",
"name": "Sustainability & Governance",
"value": 71,
"weight": 0.23,
"metrics": [
{
"key": "maintainer_resilience",
"band": "weak",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 49,
"inputs": {
"bus_factor": 2,
"contributors_sampled": 8,
"top_contributor_share": 0.422
},
"components": [
{
"key": "bus_factor",
"name": "Bus factor",
"detail": "2 contributor(s) cover half of all commits",
"points": 25.2,
"status": "partial",
"details": [
{
"code": "bus_factor",
"params": {
"count": 2
}
}
],
"max_points": 54
},
{
"key": "commit_distribution",
"name": "Commit distribution",
"detail": "top contributor authored 42% of commits",
"points": 13,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 42
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "8 contributors",
"points": 10.8,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 8
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 0 contributing companies or organizations -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "excellent",
"name": "Issue & PR responsiveness",
"note": "Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"newcomer_pr_acceptance"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 84,
"inputs": {
"merged_prs": 99,
"open_issues": 0,
"closed_issues": 1,
"prs_merged_7d": null,
"prs_decided_7d": null,
"prs_merged_30d": null,
"prs_decided_30d": null,
"issue_closed_ratio": 1,
"closed_unmerged_prs": 2,
"first_time_authors_30d": null,
"first_time_prs_merged_30d": null,
"first_time_prs_decided_30d": null
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "100% of issues closed",
"points": 42,
"status": "met",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 100
}
}
],
"max_points": 42
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "99/101 decided PRs merged",
"points": 29.4,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 99,
"decided": 101
}
}
],
"max_points": 30
},
{
"key": "newcomer_pr_acceptance",
"name": "Newcomer PR acceptance",
"detail": "no first-time contributor's PR decided in 30d",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_newcomer_prs",
"params": {
"days": 30
}
}
],
"max_points": 13
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 4/30 approved changesets -- score normalized to 1",
"points": 1.5,
"status": "partial",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "moderate",
"name": "Ownership & stewardship",
"note": null,
"notes": [],
"value": 61,
"inputs": {
"followers": 24,
"owner_type": "Organization",
"is_verified": null,
"owner_login": "mobilint",
"public_repos": 20,
"account_age_days": 2055
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "organization-owned",
"points": 30,
"status": "met",
"details": [
{
"code": "owner_organization",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "24 followers of mobilint",
"points": 10.1,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 24,
"login": "mobilint"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "20 public repos, account ~5 yr old",
"points": 20.9,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 20
}
},
{
"code": "account_age_years",
"params": {
"years": 5
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "exceptional",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"mblt-model-zoo"
],
"ecosystems": "pypi",
"any_deprecated": false,
"min_days_since_publish": 0
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "1 package(s) on pypi",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 1,
"ecosystems": "pypi"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 0 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 0
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "31 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 31
}
}
],
"max_points": 20
},
{
"key": "not_deprecated",
"name": "Not deprecated",
"detail": "active, not deprecated or yanked",
"points": 20,
"status": "met",
"details": [
{
"code": "package_not_deprecated",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "good",
"name": "Engineering Quality",
"value": 77,
"weight": 0.19,
"metrics": [
{
"key": "engineering_practices",
"band": "good",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 78,
"inputs": {
"has_ci": true,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": true,
"has_precommit_config": true
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": "2 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 2
}
}
],
"max_points": 24
},
{
"key": "tests_present",
"name": "Tests present",
"detail": null,
"points": 24,
"status": "met",
"details": [],
"max_points": 24
},
{
"key": "linter_config",
"name": "Linter config",
"detail": null,
"points": 16,
"status": "met",
"details": [],
"max_points": 16
},
{
"key": "pre_commit_hooks",
"name": "Pre-commit hooks",
"detail": null,
"points": 9.6,
"status": "met",
"details": [],
"max_points": 9.6
},
{
"key": "editorconfig",
"name": ".editorconfig",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.4
},
{
"key": "openssf_scorecard_ci_tests",
"name": "OpenSSF Scorecard: CI-Tests",
"detail": "7 out of 26 merged PRs checked by a CI test -- score normalized to 2",
"points": 4,
"status": "partial",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "good",
"name": "Documentation",
"note": null,
"notes": [],
"value": 75,
"inputs": {
"topics": [
"ai-accelerators",
"edge-ai",
"quantization",
"mobilint",
"computer-vision",
"quantized-neural-networks",
"transformer"
],
"has_wiki": true,
"homepage": "https://www.mobilint.com/",
"has_readme": true,
"has_docs_dir": false,
"has_description": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 30,
"status": "met",
"details": [],
"max_points": 30
},
{
"key": "documentation_directory",
"name": "Documentation directory",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": "https://www.mobilint.com/",
"points": 15,
"status": "met",
"details": [],
"max_points": 15
},
{
"key": "repository_description",
"name": "Repository description",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "topics",
"name": "Topics",
"detail": "7 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 7
}
}
],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "moderate",
"name": "Security",
"value": 53,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "moderate",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Branch-Protection, Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"branch_protection",
"signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 53,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 16,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 2,
"scorecard_aggregate": 5.3
},
"components": [
{
"key": "binary_artifacts",
"name": "Binary-Artifacts",
"detail": "no binaries found in the repo",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "branch_protection",
"name": "Branch-Protection",
"detail": "internal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "7 out of 26 merged PRs checked by a CI test -- score normalized to 2",
"points": 0.5,
"status": "partial",
"details": [],
"max_points": 2.5
},
{
"key": "cii_best_practices",
"name": "CII-Best-Practices",
"detail": "no effort to earn an OpenSSF best practices badge detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "code_review",
"name": "Code-Review",
"detail": "Found 4/30 approved changesets -- score normalized to 1",
"points": 0.8,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 0 contributing companies or organizations -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no dangerous workflow patterns detected",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "dependency_update_tool",
"name": "Dependency-Update-Tool",
"detail": "no update tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is not fuzzed",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file detected",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "packaging",
"name": "Packaging",
"detail": "packaging workflow detected",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "SAST tool is not run on all commits -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "token_permissions",
"name": "Token-Permissions",
"detail": "detected GitHub workflow tokens with excessive permissions",
"points": 6.8,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "0 existing vulnerabilities detected",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "high_risk_jurisdiction_exposure",
"band": "exceptional",
"name": "High-Risk Jurisdiction Exposure",
"note": "Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.",
"notes": [
{
"code": "jurisdiction_evidence_limits",
"params": {}
}
],
"value": 100,
"inputs": {
"meaning": "self-published location evidence; not nationality or citizenship",
"red_flag": false,
"exposures": [],
"policy_countries": [
"Russia",
"Iran",
"North Korea"
],
"commit_weight_rule": {
"min_commits": 50,
"min_commit_share": 0.1
},
"review_only_matches": 0,
"below_threshold_exposures": [],
"assessed_self_published_locations": 2
},
"components": [
{
"key": "policy_exposure_multiplier",
"name": "Policy exposure multiplier",
"detail": "no confirmed policy-scope location match",
"points": 100,
"status": "met",
"details": [
{
"code": "jurisdiction_no_match",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "moderate",
"name": "AI Readiness",
"value": 60,
"weight": 0.04,
"metrics": [
{
"key": "ai_agent_context",
"band": "excellent",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 85,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.84,
"agent_instruction_files": [
"AGENTS.md",
"CLAUDE.md"
],
"agent_instruction_max_bytes": 15421
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "AGENTS.md, CLAUDE.md",
"points": 45,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "AGENTS.md, CLAUDE.md"
}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "84 of 100 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 84,
"sampled": 100
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "weak",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 43,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [],
"has_dockerfile": false,
"typed_language": false,
"bootstrap_files": [],
"has_devcontainer": false,
"has_linter_config": true,
"typecheck_configs": [],
"agent_commit_share": 0.11,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "automated_tests",
"name": "Automated tests",
"detail": null,
"points": 22,
"status": "met",
"details": [],
"max_points": 22
},
{
"key": "lint_format_config",
"name": "Lint / format config",
"detail": null,
"points": 11,
"status": "met",
"details": [],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "11 of the last 100 commits agent-authored or agent-credited",
"points": 10,
"status": "met",
"details": [
{
"code": "agent_authored_commits",
"params": {
"count": 11,
"sampled": 100
}
}
],
"max_points": 10
},
{
"key": "automated_maintenance",
"name": "Automated maintenance",
"detail": "no automated dependency updates observed",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_dependency_automation",
"params": {}
}
],
"max_points": 8
},
{
"key": "openssf_scorecard_pinned_dependencies",
"name": "OpenSSF Scorecard: Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "moderate",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 53,
"inputs": {
"primary_language": "Python",
"largest_source_bytes": 167903,
"source_files_sampled": 352,
"oversized_source_files": 11
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "Python without a type-check config",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_typecheck_config_language",
"params": {
"language": "Python"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "11/352 source files over 60KB",
"points": 53.3,
"status": "partial",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 352,
"oversized": 11
}
}
],
"max_points": 55
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight: agent tooling is a real maintenance signal, but its absence must never gate the top of the scale (calibration saturates at raw 91, so 100/100 remains reachable with AI Readiness at zero)."
}
],
"classification": {
"labels": [
"library"
],
"scores": {
"library": 6
},
"primary": "library",
"evidence": [
{
"tier": "distribution",
"label": "library",
"source": "registry:pypi",
"weight": 6
}
],
"artifacts": [],
"confidence": "medium",
"host_extension": false,
"runs_as_process": false,
"consumed_by_code": true
},
"metrics_version": "2.3.1"
},
"warnings": [
"Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token",
"deps.dev does not index pypi:mblt-model-zoo@2.3.0; advisories assessed against the repository dependency graph instead",
"No resolved dependencies carried a version and a supported ecosystem"
],
"report_type": "repository",
"generated_at": "2026-08-01T04:48:02.895858Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/m/mobilint/mblt-model-zoo.svg",
"full_name": "mobilint/mblt-model-zoo",
"license_state": "standard",
"license_spdx": "BSD-3-Clause"
}Las puntuaciones son señales, no garantías. Reflejan prácticas públicamente visibles en GitHub; no son una auditoría de código ni una garantía de seguridad.
Los datos ausentes se excluyen y los pesos se renormalizan; nunca se puntúan como cero. La metodología es versionada y abierta: métricas v2.3.1, esquema v0.27.0 — metodología completa · wiki de métricas.
Cómo se sitúa un resultado dentro del registro general: estadísticas agregadas — PyPI.