Skip to content
Agentmart
Submit a tool

perf-profiling-specialist

Subagent "perf-profiling-specialist" from NVIDIA/TensorRT-LLM: Expert in GPU performance profiling for TRT-LLM workloads with nvidia-smi, Nsight Systems (nsys…

Template by NVIDIA

IndexedNOASSERTION★ 14,937
Write a review

Install

Works with Claude Code. Read the repository before you give any tool access to your data.

curl -fsSL https://raw.githubusercontent.com/NVIDIA/TensorRT-LLM/main/.claude/agents/perf-profiling-specialist.md -o perf-profiling-specialist.md

Read it and adapt it to your project before use.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

A Claude Code subagent definition in NVIDIA/TensorRT-LLM. Its description says: Expert in GPU performance profiling for TRT-LLM workloads with nvidia-smi, Nsight Systems (nsys timeline capture + per-iteration trace analysis), Nsight Compute (ncu kernel-level analysis), and PyTorch profiler. This agent can execute shell commands directly. Delegate to this agent for: (1) Running workloads (Python scripts, CUDA binaries, shell commands), (2) Measuring performance metrics (throughput, latency, MFU, SOL%, GPU utilization, memory bandwidth, tensor core usage), (3) Capturing and analyzing profiler traces, (4) Benchmarking kernels and comparing performance before/after optimizati Tools it asks for: Read, Write, Edit, Bash, Grep, Glob.

Use cases: monitoring-observability, testing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

What's in it

A Claude Code subagent: a Markdown file with frontmatter that defines a specialised helper agent and the tools it may use.

For
Claude Code
Length
417 lines
File
.claude/agents/perf-profiling-specialist.md
name
perf-profiling-specialist
tools
Read, Write, Edit, Bash, Grep, Glob
description
Expert in GPU performance profiling for TRT-LLM workloads with nvidia-smi, Nsight Systems (nsys timeline capture + per-iteration trace analysis), Nsight Compute (ncu kernel-level analysis), and PyTorch profiler. This agent can execute shell commands directly. Delegate to this agent for: (1) Running workloads (Python scripts, CUDA binaries, shell commands), (2) Measuring performance metrics (throughput, latency, MFU, SOL%, GPU utilization, memory bandwidth, tensor core usage), (3) Capturing and a

Sections

  1. Intent-Driven Routing
  2. Metric-to-Skill Mapping
  3. Core Capabilities
  4. Safe Modification Workflow
  5. Key Metrics
  6. Profiling Workflow
  7. Distributed Capture
  8. nsys SQLite Direct Queries
  9. TRT-LLM Environment Variables
  10. Key TRT-LLM Kernel Families
  11. Key TRT-LLM Source Paths
  12. Structured Output
  13. Error Handling
  14. Scope Boundaries

The repository's license isn't open source, so the text isn't shown here. Read it on GitHub.

Signals

Stars
14,937
Forks
2,862
Open issues
679
Last commit (this folder)
Oct 19, 2026 (10 days ago)
Last release
Apr 20, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
NOASSERTION
Repository
github.com/NVIDIA/TensorRT-LLM
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from NVIDIA

Cite this page

perf-profiling-specialist. Agent Mart. https://agentmart.dev/templates/nvidia-tensorrt-llm-perf-profiling-specialist (last updated 2026-10-24)