Awamer awamer.ai
عربي

NVIDIA/TensorRT-LLM/perf-host-analysis

TensorRT-LLM NVIDIA

> Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces.

How to get this skill

Agent Skill by NVIDIA. Download or clone it, then install it in your agent.

View on GitHub ⬇ Download ZIP Publisher: NVIDIA

Setup & Installation

  1. Clone the repository: git clone https://github.com/NVIDIA/skills.git
  2. Copy the skill folder (which contains SKILL.md) into your agent skills folder, e.g. .claude/skills/.
  3. Restart or reload the agent to auto-discover the skill.
  4. Check SKILL.md for any special instructions or requirements.

Related skills

TensorRT-LLM

NVIDIA/TensorRT-LLM/ad-accuracy-debug

> Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline).

NVIDIA Details →
TensorRT-LLM

NVIDIA/TensorRT-LLM/ad-add-fusion-transformation

> Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout.

NVIDIA Details →
TensorRT-LLM

NVIDIA/TensorRT-LLM/ad-conf-check

> Check whether AutoDeploy YAML configs were actually applied by analyzing server logs and optionally graph dumps (AD_DUMP_GRAPHS_DIR).

NVIDIA Details →
TensorRT-LLM

NVIDIA/TensorRT-LLM/ad-graph-dump

> Enable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR.

NVIDIA Details →