perf-analysis

Performance analysis coordination workflow. Guides profiling delegation, bottleneck classification (compute/memory/launch/communication/sync), and structured report generation. Use when the user asks to analyze performance, profile a workload, check MFU/SOL, or diagnose bottlenecks.

Jump to install Review files

Repository: NVIDIA/TensorRT-LLM
Last source activity: October 19, 2026 at 15:24
Detected SKILL.md language: English
Stars: 15,066
Forks: 2,929

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/NVIDIA/TensorRT-LLM/tree/main/.claude/skills/perf-analysis.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/NVIDIA/TensorRT-LLM --skill perf-analysis

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

name	perf-analysis
description	Performance analysis coordination workflow. Guides profiling delegation, bottleneck classification (compute/memory/launch/communication/sync), and structured report generation. Use when the user asks to analyze performance, profile a workload, check MFU/SOL, or diagnose bottlenecks.

Back to search Back to installation

trtllm-modeling-v2-entry

Load before implementing, modifying or certifying a TensorRT-LLM ModelingV2 catalog entry (OpWrapper) or its GPU test, including verification at new shapes/dtypes/architectures and target-local variants. Not needed for catalog discovery, assembling a target from unchanged entries, running model-level gates, or tuning serving settings.

2026-11-09

trtllm-modeling-v2-features

Load when working on, testing or debugging a TensorRT-LLM engine feature around a ModelingV2 target -- KV-cache block (prefix) reuse, disaggregated serving, chunked prefill, KV-cache dtype (fp8/nvfp4 and their scales), CUDA graphs and the overlap scheduler, multimodal inputs, speculative decoding, or attention-DP/TP/EP where it changes one of those -- including a check that fails on a feature field, or a number that moves only with a feature on. Says which engine stage owns the feature and what the target must honour, where its code and tests are in the tree, and how to prove it from a CPU check up to the flow's accuracy, disagg or acceptance gate. Not needed to write or certify one catalog entry (trtllm-modeling-v2-entry) or to debug core accuracy with every feature at its default.

2026-11-09

trtllm-moe-develop

Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability. Always use for any modification, review, refactor, or design planning that touches MoE modules, including tensorrt_llm/_torch/moe/fused_moe, ConfigurableMoE, MoE implementations (MoEImplBase leaves and families), backend selection (moe_resolution, can_implement, implementation identities), MoEScheduler/moe_scheduler.py, forward execution/chunking, communication strategies, EPLB, quantization/weight handling, activation support, routing, factories, MoE docs, or MoE tests. Also use when the user asks whether a MoE design follows the current architecture or whether a MoE refactor is reasonable.

2026-11-08

View all from this repository

perf-analysis

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository