NVIDIA/TensorRT-LLM/ad-accuracy-debug A
NVIDIA/skills
Agent Skill
Active
Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline).
NVIDIA/TensorRT-LLM/exec-local-compile
NVIDIA/skills/skills/TensorRT-LLM/exec-local-compile
Agent Skill
Active
Apache-2.0
Compile TensorRT-LLM on a compute node inside a Docker container.
A Quality 85/100
★ 2.9k stars
Updated today
Python
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/Quality score breakdown
Transparent heuristic — same formula for every entry. Total 85/100.
GitHub stars (log scale)35/40
Maintenance activity25/25
License present10/10
Official project0/10
Not archived5/5
Meaningful description5/5
Repo topics set5/5
Related in TensorRT-LLM
NVIDIA/TensorRT-LLM/ad-add-fusion-transformation A
NVIDIA/skills
Agent Skill
Active
Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout.
NVIDIA/TensorRT-LLM/ad-conf-check A
NVIDIA/skills
Agent Skill
Active
Check whether AutoDeploy YAML configs were actually applied by analyzing server logs and optionally graph dumps (AD_DUMP_GRAPHS_DIR).
NVIDIA/TensorRT-LLM/ad-graph-dump A
NVIDIA/skills
Agent Skill
Active
Enable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR.
NVIDIA/TensorRT-LLM/ad-layer-visualizer A
NVIDIA/skills
Agent Skill
Active
Visualize a specific transformer decoder layer from an AutoDeploy FX graph text dump as a hierarchical DOT/PNG diagram.
NVIDIA/TensorRT-LLM/ad-model-onboard A
NVIDIA/skills
Agent Skill
Active
Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.