Stars
★ 2.8k
Agent Skill
Active
Apache-2.0
NVIDIA/TensorRT-LLM/exec-local-compile
Compile TensorRT-LLM on a compute node inside a Docker container.
Quality score 84/100
Installation
Install this skill (Claude Code)
# Clone and copy the skill into your project
git clone https://github.com/NVIDIA/skills.git
mkdir -p .claude/skills
cp -r skills/skills/TensorRT-LLM/exec-local-compile .claude/skills/
# Or for personal use: ~/.claude/skills/Related in TensorRT-LLM
Agent Skill
Active
NVIDIA/TensorRT-LLM/ad-accuracy-debug
Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline).
Agent Skill
Active
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.
Agent Skill
Active
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).
Agent Skill
Active
NVIDIA/TensorRT-LLM/ad-graph-dump
Enable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR.
Agent Skill
Active
NVIDIA/TensorRT-LLM/ad-layer-visualizer
Visualize a specific transformer decoder layer from an AutoDeploy FX graph text dump as a hierarchical DOT/PNG diagram.
Agent Skill
Active
NVIDIA/TensorRT-LLM/ad-model-onboard
Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.