Run TLX kernel performance benchmarks on Hopper, Blackwell, and AMD (gfx950/CDNA4, gfx1250) GPUs.
$ npx skills add facebookexperimental/triton --skill kernel-perf-testing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install facebookexperimental/triton kernel-perf-testing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/facebookexperimental/triton.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/kernel-perf-testing .claude/skills/kernel-perf-testing && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "kernel-perf-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/kernel-perf-testing into .claude/skills/kernel-perf-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-perf-testing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/facebookexperimental/triton/tree/main/.claude/skills/kernel-perf-testingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add facebookexperimental/triton --skill kernel-perf-testing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install facebookexperimental/triton kernel-perf-testing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facebookexperimental/triton.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/kernel-perf-testing .agents/skills/kernel-perf-testing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "kernel-perf-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/kernel-perf-testing into .agents/skills/kernel-perf-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-perf-testing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add facebookexperimental/triton --skill kernel-perf-testing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install facebookexperimental/triton kernel-perf-testing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facebookexperimental/triton.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/kernel-perf-testing .cursor/skills/kernel-perf-testing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "kernel-perf-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/kernel-perf-testing into .cursor/skills/kernel-perf-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-perf-testing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/facebookexperimental/triton.git --path .claude/skills/kernel-perf-testing--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add facebookexperimental/triton --skill kernel-perf-testing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install facebookexperimental/triton kernel-perf-testing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facebookexperimental/triton.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/kernel-perf-testing .gemini/skills/kernel-perf-testing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "kernel-perf-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/kernel-perf-testing into .gemini/skills/kernel-perf-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-perf-testing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install facebookexperimental/triton kernel-perf-testingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add facebookexperimental/triton --skill kernel-perf-testing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/facebookexperimental/triton.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/kernel-perf-testing .github/skills/kernel-perf-testing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "kernel-perf-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/kernel-perf-testing into .github/skills/kernel-perf-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-perf-testing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add facebookexperimental/triton --skill kernel-perf-testing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install facebookexperimental/triton kernel-perf-testing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/facebookexperimental/triton.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/kernel-perf-testing .opencode/skills/kernel-perf-testing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "kernel-perf-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/kernel-perf-testing into .opencode/skills/kernel-perf-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kernel-perf-testing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
kernel-perf-testingRun TLX kernel performance benchmarks on Hopper, Blackwell, and AMD (gfx950/CDNA4, gfx1250) GPUs.
Kernel Perf Testing is an agent skill from facebookexperimental/triton, published by the product's own GitHub organization. Run TLX kernel performance benchmarks on Hopper, Blackwell, and AMD (gfx950/CDNA4, gfx1250) GPUs. Use when user asks to benchmark, profile, or measure performance of any TLX kernel (GEMM, Flash Attention, addmm+GLU, IKBO variants). Handles GPU selection, denoise wrapping (NVIDIA only), and version flags. Never run unless explicitly asked.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. It works with NVIDIA AI Platform. The repository describes itself as: Github mirror of trition-lang/triton repo. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 77b4a53. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Kernel Perf Testing loads about 1.1k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 237 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from facebookexperimental/triton at commit 77b4a53, republished under its MIT licence (© facebookexperimental). 237 words, ~1,062 tokens.
.claude/skills/kernel-perf-testing/SKILL.md (or your agent's skills folder).Never run performance tests unless the user explicitly asks.
Perf scripts live in third_party/tlx/tutorials/testing/test_<arch>_<op>_perf.py,
one per (op, input-contract, arch). Each takes [--version ...] to select a
kernel variant; with no --version it runs all variants for that op.
nvidia-smi to check GPU occupancy.CUDA_VISIBLE_DEVICES to that GPU.Wrap benchmarks with denoise.sh (locks clocks/power) for stable results.
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_hopper_gemm_perf.py [--version {ws|pipelined}]
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_hopper_fa_perf.py [--version ws_pipelined_pingpong]CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_blackwell_gemm_perf.py [--version {ws|clc|pipelined|2cta}]
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_blackwell_fa_perf.py [--version {ws|ws_persistent|ws_pipelined|ws_pipelined_persistent|clc}] [--mode fwd|bwd]
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_blackwell_fa_mxfp8_perf.pydenoise.sh works on AMD too: it runs the wrapped command with NUMA pinning. Its
GPU clock/power lock is implemented with nvidia-smi, so on AMD that part is
simply skipped (no clock lock) — expect a bit more run-to-run variance.
Pick a free GPU with rocm-smi (check GPU use (%) / VRAM). denoise.sh reads
CUDA_VISIBLE_DEVICES, which torch on ROCm also honors for device selection.
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_amd_gemm_perf.py [--version {warp_pipeline|pipelined}] [--dtype fp16|bf16]
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_amd_fa_perf.py [--version {simple|prefetch|persistent}]
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_amd_addmm_glu_perf.py [--version {tlx_baseline|tlx_simple_async|tlx_optimized_async|tlx_optimized|tlx_persistent}]
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_amd_ikbo_fa_perf.py # IKBO Flash Attention
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_amd_ikbo_lce_perf.py # IKBO LCE (distinct op, not attention)CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/testing/test_amd_mxfp_gemm_perf.py [--version {tdm_pipelined}] [--transpose-b]Each script self-gates (is_hip, is_hip_cdna4, or is_hip_gfx1250) and prints
"Skipping benchmarks" on the wrong hardware.
CUDA_VISIBLE_DEVICES=<gpu_id> third_party/tlx/denoise.sh python third_party/tlx/tutorials/<KERNEL.py>Run third_party/tlx/killgpu.sh to kill GPU processes that have been running too long.
pytorch_baseline for addmm+GLU.denoise.sh is being used).© facebookexperimental, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/kernel-perf-testing of facebookexperimental/triton.
Open the folder on GitHubat commit 77b4a53
Kernel Perf Testing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Kernel Perf Testing this skillfacebookexperimental/triton | 201 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Fla Triton To Gluonfla-org/flash-linear-attention | 5.8k | — | ~4.2k | Automated safety check: Pass | MIT | |
| DGX Spark Memory and Thermal Opswshobson/agents | 40k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| DGX Spark Training Gotchaswshobson/agents | 40k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| Yolo Detection 2026SharpAI/DeepCamera | 3.1k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Sglang Diffusion Modelopt Quantsgl-project/sglang | 37k | 2 repos | ~5k | Automated safety check: Pass | Apache-2.0 |
fla-org/flash-linear-attention
Workflow for porting an existing Triton kernel in fla/ops/ to Gluon (triton.experimental.gluon) to gain explicit control over tensor layouts, shared memory, async data movement (cp.async / TMA), MMA…
wshobson/agents
Plans memory headroom, works through out-of-memory failures and watches temperature and power during long ML training jobs on NVIDIA DGX Spark.
wshobson/agents
Preflight checks and diagnosis for ten known failure modes of ML training on NVIDIA DGX Spark's GB10, spanning launch errors, memory, thermals, bandwidth and precision.
SharpAI/DeepCamera
YOLO 2026 — state-of-the-art real-time object detection. An agent skill from SharpAI/DeepCamera.
sgl-project/sglang
A skill your agent uses when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.
brevdev/workshop-build-an-agent
Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.
facebookexperimental/triton
Collect, validate, package, and inspect rocprofv3 Advanced Thread Trace bundles for AMD GPU kernels.
facebookexperimental/triton
Design and run Triton TTGIR debugging ablations using iroverride.
facebookexperimental/triton
Execute the TLX Kernel Optimization Agent CLI on a Triton or TLX kernel.
facebookexperimental/triton
Run NVIDIA compute-sanitizer (memcheck, racecheck, initcheck, synccheck) against a Triton/TLX kernel to find runtime memory and synchronization bugs.
facebookexperimental/triton
Recover from GPU-busy / GPU-unavailable failures. An agent skill from facebookexperimental/triton.
facebookexperimental/triton
Debug Triton compilation by dumping IR at each stage (TTIR, TTGIR, LLVM, PTX).
Works with
Categories
Run TLX kernel performance benchmarks on Hopper, Blackwell, and AMD (gfx950/CDNA4, gfx1250) GPUs. Kernel Perf Testing is an agent skill from facebookexperimental/triton, published by the product's own GitHub organization. Run TLX kernel performance benchmarks on Hopper, Blackwell, and AMD (gfx950/CDNA4, gfx1250) GPUs.
Kernel Perf Testing fits situations like: user asks to benchmark; measure performance of any TLX kernel (GEMM; flash Attention.
Run `npx skills add facebookexperimental/triton --skill kernel-perf-testing -a claude-code`. Or copy the skill folder (.claude/skills/kernel-perf-testing in facebookexperimental/triton) into .claude/skills/kernel-perf-testing in your project. Claude Code loads it when a task matches its description.
Run `npx skills add facebookexperimental/triton --skill kernel-perf-testing -a codex`. Or copy the skill folder (.claude/skills/kernel-perf-testing in facebookexperimental/triton) into .agents/skills/kernel-perf-testing in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add facebookexperimental/triton --skill kernel-perf-testing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kernel-perf-testing, .gemini/skills/kernel-perf-testing, .github/skills/kernel-perf-testing and .opencode/skills/kernel-perf-testing in your project.
SKILL.md names no scripts, command-line tools or credentials: Kernel Perf Testing is instructions for the agent only. Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Kernel Perf Testing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Kernel Perf Testing: Fla Triton To Gluon (fla-org/flash-linear-attention, 5.8k stars), DGX Spark Memory and Thermal Ops (wshobson/agents, 40k stars), DGX Spark Training Gotchas (wshobson/agents, 40k stars) and Yolo Detection 2026 (SharpAI/DeepCamera, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
facebookexperimental (a GitHub organization, an official publisher) maintains it in facebookexperimental/triton, which has 201 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 7, 2026.
Source: facebookexperimental/triton on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
