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.
npx agentmods add skills/flashinfer-ai/flashinfer/benchmark-kernelnpx skills add flashinfer-ai/flashinfer --skill benchmark-kernelgit clone --depth 1 https://github.com/flashinfer-ai/flashinferWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00014 | $0.03602 |
| Opus 5 | $0.00007 | $0.01801 |
| Sonnet 5 | $0.00003 | $0.00720 |
| Haiku 4.5 | $0.00001 | $0.00360 |
Grade B, and why
benchmark-kernel scanned grade B with 1 finding 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 3d ago.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo nvidia-smi -lgc <base_clock> How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutorial: Benchmarking FlashInfer Kernels
This tutorial shows you how to accurately benchmark FlashInfer kernels.
Goal
Measure the performance of FlashInfer kernels:
- Get accurate GPU kernel execution time
- Compare multiple backends (FlashAttention2/3, cuDNN, CUTLASS, TensorRT-LLM)
- Generate reproducible benchmark results
- Save results to CSV for analysis
Timing Methods
FlashInfer supports two timing methods:
-
CUPTI (Preferred): Hardware-level profiling for most accurate GPU kernel time
- Measures pure GPU compute time without host-device overhead
- Requires
cupti-python >= 13.0.0(CUDA 13+)
-
CUDA Events (Fallback): Standard CUDA event timing
- Automatically used if CUPTI is not available
- Good accuracy, slight overhead from host synchronization
The framework automatically uses CUPTI if available, otherwise falls back to CUDA events.
Autotuner timing (separate from the benchmark framework above). The
AutoTuner's internal per-tactic timing has its own selector,FLASHINFER_AUTOTUNE_TIMER:globaltimerforces the GPU%globaltimerregister,cuda_eventforcescudaEvent, and unset/auto uses%globaltimeronly when Confidential Computing (CC) is detected. Under CCcudaEventElapsedTimeis unreliable (can go negative), which would corrupt tactic ranking — the globaltimer path avoids that. CC auto-detection can be overridden withFLASHINFER_CONFIDENTIAL_COMPUTE=0/1. (Full env-var reference inCLAUDE.md.)
Installation
Install CUPTI (Recommended)
For the most accurate benchmarking:
pip install -U cupti-python
Requirements: CUDA 13+ (CUPTI version 13+)
Without CUPTI
If you don't install CUPTI, the framework will:
- Print a warning:
CUPTI is not installed. Falling back to CUDA events. - Automatically use CUDA events for timing
- Still provide good benchmark results
Method 1: Using flashinfer_benchmark.py (Recommended)
Step 1: Choose Your Test Routine
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.
- 3d ago First seen · 433 lines · 14 tokens per session scan B 597917dae005
benchmark-kernel is a skill published in the GitHub repository flashinfer-ai/flashinfer (6,312 stars, last pushed yesterday), licensed Apache-2.0. It adds 14 tokens to every session and 3,602 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
megakernel-optimization
Use when optimizing or generating a CUDA megakernel for a HuggingFace Llama-family model with AutoMegaKernel (AMK), drives the correctness-gated propose -> eval -> keep/revert loop (or hands off to the unattended autoresearch driver).
gpu-server-setup
Prepare a Linux server with NVIDIA GPUs for neural-network and LLM workloads, or diagnose one that misbehaves. Use when the user asks to set up or prepare a GPU server, install NVIDIA drivers or CUDA on Debian/Ubuntu, wire Docker to GPUs (NVIDIA Container Toolkit), deploy vLLM / Infinity / OpenWebUI / Ollama /…
cuopt-skill-evolution
After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
cuopt-developer
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
cuopt-user-rules
Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.
trtllm-model-onboard-multimodal
Onboard a HuggingFace multimodal model (vision/audio/video + text) to the TensorRT-LLM PyTorch backend. Use when writing a new tensorrtllm/torch/models/modeling .py plus its input processor and weight mapper, or extending an existing VLM. Not for AutoDeploy — use ad-model-onboard for that path.