Skip to main content

forward-kernel-validation

Validate optimized Recirculation forward kernels against an unfused, unbatched oracle when changing batching, fusion, attention, CUDA graphs, or accelerator inference code.

Informations de source

Dépôt
ModelCloud/Recirculation
Dernière activité de la source
22 août 2026 à 12:54
Langue détectée de SKILL.md
anglais
Étoiles
9
Forks
4

Options d'installation

Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.

Vérifiez les fichiers source

Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.

Affichage de SKILL.md

SKILL.md
Instructions source · Aperçu en lecture seule
name
forward-kernel-validation
description
Validate optimized Recirculation forward kernels against an unfused, unbatched oracle when changing batching, fusion, attention, CUDA graphs, or accelerator inference code.
# Forward kernel validation Compare optimized forward outputs with the unfused, unbatched implementation using identical weights, dtype, tokens, positions, masks, cache state, and Recirculation configuration. Use mean absolute forward error as the release gate: - Fused or batched kernels: mean absolute error must be at most `4e-3`. - Kernels that are both non-fused and non-batched: mean absolute error must be at most `2e-3`. A path qualifies for the `4e-3` limit if it uses fusion, batching, or both. Record max absolute error, relative L2, and normalized max for diagnostics, but do not use those metrics to accept or reject the kernel. A stricter explicitly requested gate may still be used. Benchmark accuracy, task scores, and greedy-token agreement are outcome diagnostics, not substitutes for the forward gate. Do not reject an otherwise passing optimization solely because a benchmark score or greedy output changes; report those changes separately. Save the selected gate, kernel classification, oracle configuration, and all error metrics with benchmark artifacts.
Voir sur GitHub