Skills · davila7

inference-serving-tensorrt-llm

A skill for optimizing LLM inference with NVIDIA TensorRT, aimed at production serving on NVIDIA GPUs.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

This skill guides the optimization of large language model inference with NVIDIA TensorRT. It covers model quantization (FP8 and INT4), in-flight batching and scaling across multiple GPUs.

It is intended for production deployment on NVIDIA GPUs such as the A100 and H100, and for cases where faster inference than PyTorch is needed. The publisher states speedups of 10-100x over PyTorch.

The publisher's description does not list setup steps. It is distributed under the MIT license as part of the claude-code-templates collection.

Limitations and requirements

Requires NVIDIA GPUs; the publisher names the A100 and H100. The 10-100x speedup over PyTorch is the publisher's own figure.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 60
    inference-serving-tensorrt-llm

    Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

    v1.0.0
    As shown on www.aitmpl.com when we last read it
Not reviewedSkills
wshobson

Connectivity triage

A skill published by wshobson for connectivity triage, with no further documentation available in its source.

AI agents & models
Updated 14 Nov 2026
Not reviewedSkills
wshobson

Saga orchestration (wshobson)

A saga orchestration skill published by wshobson, listed under the backend-development plugin in the agents repository.

Software development
Updated 14 Nov 2026
Not reviewedSkills
github

Flowstudio Power Automate Debug

A GitHub-published skill, named for debugging Power Automate flows, listed under development and productivity.

Software developmentProductivity & automation
Updated 18 Nov 2026
Not reviewedSkills
davila7

flowio: FCS file parser for flow cytometry data

A skill for parsing Flow Cytometry Standard (FCS) files, versions 2.0 to 3.1, as part of flow cytometry data preprocessing.

Software developmentData & databases
Updated 18 Nov 2026
inference-serving-tensorrt-llm | AI Gate Discover