Skip to main content

NVIDIA/kumo-engine

Dernière activité source enregistrée
Catalogue SkillsMP mis à jour
skills collectés
17
Étoiles GitHub
38
Forks GitHub
8

Installer avec un assistant IA

Copiez ce prompt dans l’assistant IA que vous utilisez.

Chargement du README du dépôt…

Skills dans ce dépôt

classification en attente

Affichage de 17 skills collectés sur 17.

métier
non classé
description

Use for any work with KumoAI predictive models on relational data in a warehouse, an object store or local files: train a model, score data with a trained one, or answer questions about an existing model or run — explain its predictions, diagnose its…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Reference for translating a validated ML request into KumoAI graph configuration, PQL (predictive query language), and Kumo Predict SDK code. Normally loaded by the kumo-data-science skill after its intake checks pass, rather than invoked directly. Triggers:…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Inspect and interpret gradient attribution (including requests called radiant attribution), column analysis and sampled explanation subgraphs from a Kumo model trained in a Python notebook. Locate the correct run's explanation artifacts, explain feature…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Configure a Kumo model plan for a user-defined task, including encoders, run mode, bounded experiments, sampling, optimization, architecture, metrics and refits. Preserve target and evaluation constraints and use existing diagnostics for comparisons.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Evaluate an existing Kumo training run in a Python notebook using aggregate metrics, trial results, learning curves, refit evidence, and training progress. Use for model-quality questions or training diagnostics; inspect existing results without automatically…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Train with caller-supplied labels, weights and splits or score exact entity/anchor rows through Snowflake source tables using the local Kumo API. Use when generated populations do not represent the requested rows.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Publish and reload Kumo models through the Snowflake registry, reconstruct compatible scoring inputs, and retain or retrieve run diagnostics and output files through a Snowflake stage. Use for saved-model scoring and artifact retention without retraining by…

Langue du texte source : anglais

mis à jour
métier
non classé
description

Orchestrate Kumo UI ticket work from GitHub issue analysis through implementation, validation, and optional PR creation.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Use when the user asks to check, view, or search Kumo application logs from a supplied file or a selected Kubernetes deployment.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Scaffold and implement UI features following Kumo conventions. Use when creating new components, pages, hooks, stores, or tests in ui/src/.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Use when the user asks to debug, investigate, or fix a GitHub issue or supplies a repository bug report.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Use when a training or prediction job is stuck or slow at a particular stage, or its Temporal workflow status needs investigation.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Use before a debugging workflow, when asked to check the environment, or when the local CLI tools needed for the requested task are not working.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Review PR code changes against ML standards. Use when reviewing PRs that touch ML pipeline code (packages/kumo-core, kumo/pquery, kumo/train, kumo/task, kumo/automl, kumo/explain). Applies lessons learned from past ML reviews.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Review PR code changes against UI conventions. Use when reviewing PRs that touch frontend code (ui/src/). Applies lessons learned from past UI reviews and enforces coding guidelines.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Scaffold and implement UI catalog components following conventions. Use when creating new primitives, block components, stories, or tests in kumo-ui-catalog.

Langue du texte source : anglais

mis à jour
métier
non classé
description

Review PR code changes against UI catalog conventions. Use when reviewing PRs that touch components, stories, or tests in kumo-ui-catalog.

Langue du texte source : anglais

mis à jour
Affichage de 17 skills collectés sur 17.