perf-torch-cuda-graphs

perf-torch-cuda-graphs is a skill for Claude Code, Codex from NVIDIA/TensorRT-LLM. It costs 119 tokens per session (5,857 once invoked), scanned A, original, no licence file.

A guide for using CUDA Graphs, a CUDA feature that records GPU work so it can be replayed, with PyTorch workloads.

In plain words
What is it for?
Use it when adding CUDA Graphs to PyTorch code, including code that uses torch.compile, Transformer Engine, Megatron Core, or manual graph capture.
Why use it?
It helps developers choose an appropriate CUDA Graphs API, adapt code for graph capture, handle changing execution patterns, and investigate problems.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nvidia/tensorrt-llm/perf-torch-cuda-graphs
Any agent
npx skills add NVIDIA/TensorRT-LLM --skill perf-torch-cuda-graphs
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/TensorRT-LLM

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for perf-torch-cuda-graphs

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia/tensorrt-llm/perf-torch-cuda-graphs.svg)](https://agentmods.dev/skills/nvidia/tensorrt-llm/perf-torch-cuda-graphs)
Your own site
<a href="https://agentmods.dev/skills/nvidia/tensorrt-llm/perf-torch-cuda-graphs"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-llm/perf-torch-cuda-graphs.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,857 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00119 $0.05857
Opus 5 $0.00060 $0.02929
Sonnet 5 $0.00024 $0.01171
Haiku 4.5 $0.00012 $0.00586

Measured 5d ago against content hash aee437b6c16c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

perf-torch-cuda-graphs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify_workload.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/perf-torch-cuda-graphs/SKILL.md · 635 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 635 lines · 119 tokens per session scan A aee437b6c16c

Subscribe to this mod's changes

perf-torch-cuda-graphs is a skill published in the GitHub repository NVIDIA/TensorRT-LLM (14,550 stars, last pushed today), with no licence file. It adds 119 tokens to every session and 5,857 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

Orchestra-Research/AI-Research-SKILLs · 88 tokens

perf-torch-cuda-graphs

Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch makegraphedcallables, TE makegraphedcallables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph…

wenyi-li/awesome-agent-kernel-skills · 119 tokens

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

TTAWDTT/elegant-researcher-skill · 88 tokens

sglang-diffusion-add-model

Use when adding a new diffusion model or Diffusers pipeline to SGLang.

sgl-project/sglang · 24 tokens

sglang-diffusion-performance

Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.

sgl-project/sglang · 29 tokens

cookbook-add-model

Add a new model to the SGLang Cookbook (docs/, Mintlify), config-driven format — instantiate the model-agnostic template into a per-model config (+ benchmarks) JSX under src/snippets/configs/, an MDX page, the docs.json nav entry, NEW-tag hygiene, and the homepage vendor card. Interactive, multi-phase. Run with…

sgl-project/sglang · 82 tokens