Menu
SkillsMP has collected 11 skills from NVIDIA/TensorRT-Model-Connect. Open a skill to review its source and details.
Showing 11 of 11 collected skills.
Use when TensorRT output diverges from a model reference, model-first validation fails, generated text or media is wrong, or a family change introduces a numerical mismatch. Routes the investigation by model modality and escalates from the first divergent…
Use for documentation maintenance scans that keep the canonical website journey, repo-local skills, commands, API reference, architecture and design, extension guides, feature context, ADRs, and traceability status aligned with the current GitHub main branch.…
Use 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.
Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues,…
Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR…
Draft, revise, or review Git commit messages, PR titles, PR descriptions, and squash or rebase merge messages. Use when Codex needs to summarize a diff for reviewers, convert rough notes into a commit or PR message, check a message against Git and…
Use when adding, reviewing, or debugging FP16/BF16 precision in a family-owned, strongly typed TensorRT network. Covers dtype threading, explicit FP32 boundaries, typed constants, compact GQA/MQA state, bundle evidence, and low-precision validation.
Use when evaluating FP16, BF16, or supported quantization formats for a TensorRT-Model-Connect model. Establishes a model-owned correctness baseline, changes one effective build option at a time, detects ineffective precision, and retains comparable parity,…
Use when diagnosing one model's runtime cost or producing comparable TensorRT-Model-Connect performance evidence. Routes quick investigation to the unified profiler and release or qualification claims to the checked-in performance matrix and model-owned…
Prepare a TensorRT-Model-Connect development or deployment-validation environment from a fresh checkout on an unfamiliar host. Use before builds, tests, packaging, or runtime work when no working repo environment is known.
Use when onboarding a Hugging Face model into TensorRT-Model-Connect or extending an existing family to produce a `.bundle` bundle. Drives ownership-first implementation across Python builder, native runtime, and model-owned E2E descriptors, then requires…