Optimize Model Precision
NVIDIA/TensorRT-Model-Connect/plugins/trtmc-agent-skills/skills/optimize-model-precision
ai-mlResmi
Resmi Sağlayıcı Skill'iView repo
Evaluate supported precision, quantization, or selected FP32-layer choices for one TensorRT-Model-Connect family with matched correctness and timing.
Dosyalar2 dosya
SKILL.md52 satır
Loading editor…
Kurulum
ÖnerilenTek komut — ajanınız otomatik olarak devreye alır.
Kurulum komutunu görmek için yukarıdan bir AI aracı seçin.
veya
Manuel Kurulum
Daha fazla adımArşivi indirin ve dosyaları projenize manuel olarak ekleyin.
Skill detayları
Versiyonv1.0.0
YazarNVIDIA
Kategoriai-ml
Skill IDNVIDIA/TensorRT-Model-Connect/plugins/trtmc-agent-skills/skills/optimize-model-precision
Dosyalar2 dosya
İlgili skill'ler
Debug Trt MismatchDiagnose a TensorRT-Model-Connect family whose native output disagrees with its declared reference or family-owned correctness contract.Doc SyncAudit and update TensorRT-Model-Connect documentation when code, public APIs, family ownership, commands, or model support have changed.Fp16 Trt NetworkImplement or review FP16 and BF16 behavior in one family-owned, strongly typed TensorRT network without changing unrelated families.Pr BabysitterUse when monitoring GitHub pull request CI, diagnosing failed checks, rebasing branches onto github/main, applying narrowly scoped fixes, and updating PRs until their latest checks are green or a human blocker is identified.Profile ModelMeasure one TensorRT-Model-Connect model through its public Task API or run a checked-in performance-matrix entry with comparable evidence.Review Trtmc PrReview a TensorRT-Model-Connect GitHub PR or local contributor branch against the current post-#1093 model-family isolation architecture, repository rules, behavioral correctness, and exact-head validation evidence. Use for contributor self-review before marking a PR ready, or when deciding whether a community PR is compliant, decoupled, merge-ready, or needs maintainer feedback. The review is read-only unless the user separately asks to publish it or change the contribution.