Kernel Organization
sgl-project/sglang
Apply the SGLang kernels RFC when adding, moving, splitting, or reviewing kernel APIs, registry metadata, kernel tests, benchmarks, and model-specific implementations.
Test and run TLX-AMD tutorial kernels (gfx950/CDNA4 and gfx1250) and understand their CI.
OfficialMITAuto-check: notes
Install Tlx Amd Testing
$ npx skills add facebookexperimental/triton --skill tlx-amd-testing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install facebookexperimental/triton tlx-amd-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/tlx-amd-testing .claude/skills/tlx-amd-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 "tlx-amd-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/tlx-amd-testing into .claude/skills/tlx-amd-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tlx-amd-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/tlx-amd-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 tlx-amd-testing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install facebookexperimental/triton tlx-amd-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/tlx-amd-testing .agents/skills/tlx-amd-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 "tlx-amd-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/tlx-amd-testing into .agents/skills/tlx-amd-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tlx-amd-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 tlx-amd-testing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install facebookexperimental/triton tlx-amd-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/tlx-amd-testing .cursor/skills/tlx-amd-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 "tlx-amd-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/tlx-amd-testing into .cursor/skills/tlx-amd-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tlx-amd-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/tlx-amd-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 tlx-amd-testing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install facebookexperimental/triton tlx-amd-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/tlx-amd-testing .gemini/skills/tlx-amd-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 "tlx-amd-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/tlx-amd-testing into .gemini/skills/tlx-amd-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tlx-amd-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 tlx-amd-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 tlx-amd-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/tlx-amd-testing .github/skills/tlx-amd-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 "tlx-amd-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/tlx-amd-testing into .github/skills/tlx-amd-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tlx-amd-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 tlx-amd-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 tlx-amd-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/tlx-amd-testing .opencode/skills/tlx-amd-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 "tlx-amd-testing" agent skill from https://github.com/facebookexperimental/triton/tree/main/.claude/skills/tlx-amd-testing into .opencode/skills/tlx-amd-testing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tlx-amd-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.
Facts
- Skill name
tlx-amd-testing- GitHub stars
- 201
- Token cost
- ~1.3k tokens
- SKILL.md length
- 419 words
- Files
- 1
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- MIT
At a glance
Test and run TLX-AMD tutorial kernels (gfx950/CDNA4 and gfx1250) and understand their CI.
- Working on AMD TLX tutorial kernels — GEMM (warp-pipeline
- SKILL.md covers Kernel inventory, Correctness, Perf and CI, plus 1 more section
- Calls pytest and make
- Flash Attention (simple
What it does
Tlx Amd Testing is an agent skill from facebookexperimental/triton, published by the product's own GitHub organization. Test and run TLX-AMD tutorial kernels (gfx950/CDNA4 and gfx1250) and understand their CI. Use when working on AMD TLX tutorial kernels — GEMM (warp-pipeline, LDS-pipelined, TDM, MXFP), Flash Attention (simple, prefetch, persistent), addmm+GLU, or IKBO (FA, LCE) — running their correctness or perf, checking arch gating (gfx950 vs gfx1250), or the MI350 CI workflow. Covers the standardized layout (one correctness file, one perf file per op×arch).
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Github mirror of trition-lang/triton repo. The licence is MIT.
When your agent uses it
- Working on AMD TLX tutorial kernels — GEMM (warp-pipeline
- Flash Attention (simple
- LCE) — running their correctness
- Checking arch gating (gfx950 vs gfx1250)
Example prompts
- “/tlx-amd-testing”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 953bd20. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
pytestmake
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Tlx Amd Testing loads about 1.3k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 419 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.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteRuns commands with sudoSKILL.md:67
node, and resets both on exit. It needs sudo and is best-effort. It
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.
SKILL.md
The full file from facebookexperimental/triton at commit 953bd20, republished under its MIT licence (© facebookexperimental). 419 words, ~1,259 tokens.
Download SKILL.mdSave it as
.claude/skills/tlx-amd-testing/SKILL.md (or your agent's skills folder).- name
- tlx-amd-testing
- description
- Test and run TLX-AMD tutorial kernels (gfx950/CDNA4 and gfx1250) and understand their CI. Use when working on AMD TLX tutorial kernels — GEMM (warp-pipeline, LDS-pipelined, TDM, MXFP), Flash Attention (simple, prefetch, persistent), addmm+GLU, or IKBO (FA, LCE) — running their correctness or perf, checking arch gating (gfx950 vs gfx1250), or the MI350 CI workflow. Covers the standardized layout (one correctness file, one perf file per op×arch).
TLX-AMD Tutorial Kernel Testing
AMD tutorial kernels follow the same standardized layout as the NVIDIA
(Hopper/Blackwell) reference: one shared correctness file
(test_correctness.py, arch-gated) and one perf script per (op, arch).
Each kernel is an importable module under third_party/tlx/tutorials/.
Kernel inventory
| Kernel module | Op | Correctness test(s) | Perf script | Arch gate |
|---|---|---|---|---|
amd_gemm_warp_pipeline.py | GEMM | test_amd_gemm_warp_pipeline | test_amd_gemm_perf.py (warp_pipeline) | is_hip_cdna4 |
amd_gemm_pipelined.py | GEMM (LDS pipeline) | test_amd_gemm_pipelined | test_amd_gemm_perf.py (pipelined) | is_hip |
amd_gemm_gfx942.py | GEMM (MI300X, autotuned) | test_amd_gemm_gfx942, test_amd_gemm_gfx942_odd_shapes | test_amd_gemm_gfx942_perf.py | is_hip_cdna3 |
amd_addmm_gfx942.py | addmm (MI300X, autotuned) | test_amd_addmm_gfx942 | test_amd_addmm_gfx942_perf.py | is_hip_cdna3 |
amd_bmm_gfx942.py | BMM (MI300X, autotuned) | test_amd_bmm_gfx942, test_amd_bmm_gfx942_distinct_a | test_amd_bmm_gfx942_perf.py | is_hip_cdna3 |
amd_fa_pipelined.py | Flash Attention | test_amd_fa_pipelined | test_amd_fa_perf.py (simple, prefetch) | is_hip_cdna4 |
amd_fa_persistent.py | Flash Attention (persistent) | test_amd_fa_persistent, test_amd_fa_persistent_cross_attention | test_amd_fa_perf.py (persistent) | is_hip_cdna4 |
amd_addmm_glu.py | addmm + GLU (gated linear unit, not GELU) | test_amd_addmm_glu | test_amd_addmm_glu_perf.py | is_hip_cdna4 |
ikbo/ikbo_fa_triton.py | IKBO Flash Attention | test_ikbo_fa | test_amd_ikbo_fa_perf.py | none (any HIP/CUDA) |
ikbo/ikbo_lce_triton.py | IKBO LCE (logit cross-entropy — not attention) | test_ikbo_lce | test_amd_ikbo_lce_perf.py | none (any HIP/CUDA) |
amd_tdm_gemm_pipelined.py | GEMM (TDM) | test_amd_tdm_gemm_pipelined | — | is_hip_gfx1250 |
amd_mxfp_gemm_tdm_pipelined.py | GEMM (MXFP, TDM) | test_amd_mxfp_gemm_tdm_pipelined | test_amd_mxfp_gemm_perf.py | is_hip_gfx1250 |
gfx950 = CDNA4 = MI350-class (is_hip_cdna4()). gfx942 = CDNA3 = MI300X-class
(is_hip_cdna3()). gfx1250 is a separate, newer target (is_hip_gfx1250()). On
gfx950, both the gfx1250-only and the gfx942-only GEMM tests auto-skip.
The MI300X kernel is the only gfx942 entry and has no CI runner — the MI350
workflow is gfx950, so test_amd_gemm_gfx942* always skips there. Run it by hand
on an MI300X box.
Correctness
All AMD correctness lives in the single shared file; tests self-gate via
@pytest.mark.skipif, so only the relevant cases run per GPU.
# All AMD + IKBO (gfx1250-only cases auto-skip on gfx950):
pytest third_party/tlx/tutorials/testing/test_correctness.py -v -k "amd or ikbo"
# Whole file — Hopper/Blackwell cases auto-skip on AMD (what CI runs, no -k):
pytest third_party/tlx/tutorials/testing/test_correctness.py -v-k "amd" alone does not select the IKBO tests (test_ikbo_* has no "amd" in
its node id) — use -k "amd or ikbo".
Show full SKILL.md (171 more words)Show less
Perf
Never run perf unless explicitly asked. Use the kernel-perf-testing skill for
run mechanics. denoise.sh does lock clocks on AMD: it identifies the part by
PCI id (MI300X 0x74a0/0x74a1/gfx942, MI350X, MI355X), then applies
rocm-smi --setperfdeterminism (default 2100 MHz, override DETERMINISM_CLK) and
--setpoweroverdrive (750 W on MI300X, override DESIRED_POWER), NUMA-binds to
the GPU's node, and resets both on exit. It needs sudo and is best-effort. It
defaults HIP_VISIBLE_DEVICES to 4 — set it to a free GPU (rocm-smi) yourself.
CI
.github/workflows/mi350.yml runs on a gfx950 (MI350/CDNA4) runner and mirrors
.github/workflows/h100.yml:
mi350-tlx-test— TLX unit tests (python/test/unit/language/test_tlx_*.py)- the tutorial correctness suite (
test_correctness.py). AMD/IKBO run; Hopper/Blackwell and gfx1250 cases auto-skip.
- the tutorial correctness suite (
mi350-meta-triton-test— TritonBench perf coverage (perf-regression lives here, not in the perf scripts above).
Nightly failures are filed as issues via report-nightly-failure.yml.
Local run note
After any C++ change (or a stale checkout), the in-tree libtriton.so can lag
the Python source and every AMD kernel fails at compile with
AttributeError: module '...amd.passes.ttgpuir' has no attribute '<pass>'.
Fix: rebuild with make dev-install-llvm. If GPU tests hang, run
third_party/tlx/killgpu.sh.
© facebookexperimental, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/tlx-amd-testing of facebookexperimental/triton.
Open the folder on GitHubat commit 953bd20
Compare with similar skills
Tlx Amd 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 |
|---|---|---|---|---|---|---|
| Tlx Amd Testing this skillfacebookexperimental/triton | 201 | — | ~1.3k | Automated safety check: Notes | MIT | |
| Kernel Organizationsgl-project/sglang | 37k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Add Sgl Kernelsgl-project/sglang | 37k | 2 repos | ~3.4k | Automated safety check: Pass | Apache-2.0 | |
| Add Jit Kernelsgl-project/sglang | 37k | — | ~13k | Automated safety check: Pass | Apache-2.0 | |
| Metal Kernelpytorch/pytorch | 104k | — | ~4.9k | Automated safety check: Pass | Custom licence | |
| TutorialQ00/ouroboros | 6.2k | — | ~1.6k | Automated safety check: Pass | MIT |
Similar skills
Add Sgl Kernel
sgl-project/sglang
Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)
Add Jit Kernel
sgl-project/sglang
Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang.kernels JIT infrastructure and public operator groups
Metal Kernel
pytorch/pytorch
Write Metal/MPS kernels for PyTorch operators. An agent skill from pytorch/pytorch.
Tutorial
Q00/ouroboros
Interactive tutorial teaching Ouroboros hands-on. An agent skill from Q00/ouroboros.
Tutorial Engineer
sickn33/agentic-awesome-skills
Creates step-by-step tutorials and educational content from code.
More from facebookexperimental/triton
All 18 skills in this repo- Official
Amd Att Trace
facebookexperimental/triton
Collect, validate, package, and inspect rocprofv3 Advanced Thread Trace bundles for AMD GPU kernels.
- Official
Ir Override Ablation
facebookexperimental/triton
Design and run Triton TTGIR debugging ablations using iroverride.
- Official
Tlx Kernel Optimization Agent
facebookexperimental/triton
Execute the TLX Kernel Optimization Agent CLI on a Triton or TLX kernel.
- Official
Compute Sanitizer
facebookexperimental/triton
Run NVIDIA compute-sanitizer (memcheck, racecheck, initcheck, synccheck) against a Triton/TLX kernel to find runtime memory and synchronization bugs.
- Official
Debug Failing GPU
facebookexperimental/triton
Recover from GPU-busy / GPU-unavailable failures. An agent skill from facebookexperimental/triton.
- Official
Ir Debugging
facebookexperimental/triton
Debug Triton compilation by dumping IR at each stage (TTIR, TTGIR, LLVM, PTX).
Questions about Tlx Amd Testing
What does Tlx Amd Testing do?
Test and run TLX-AMD tutorial kernels (gfx950/CDNA4 and gfx1250) and understand their CI. Tlx Amd Testing is an agent skill from facebookexperimental/triton, published by the product's own GitHub organization. Test and run TLX-AMD tutorial kernels (gfx950/CDNA4 and gfx1250) and understand their CI.
When should I use Tlx Amd Testing?
Tlx Amd Testing fits situations like: working on AMD TLX tutorial kernels — GEMM (warp-pipeline; flash Attention (simple; LCE) — running their correctness; checking arch gating (gfx950 vs gfx1250).
How do I install Tlx Amd Testing in Claude Code?
Run `npx skills add facebookexperimental/triton --skill tlx-amd-testing -a claude-code`. Or copy the skill folder (.claude/skills/tlx-amd-testing in facebookexperimental/triton) into .claude/skills/tlx-amd-testing in your project. Claude Code loads it when a task matches its description.
How do I install Tlx Amd Testing in Codex?
Run `npx skills add facebookexperimental/triton --skill tlx-amd-testing -a codex`. Or copy the skill folder (.claude/skills/tlx-amd-testing in facebookexperimental/triton) into .agents/skills/tlx-amd-testing in your project. Codex loads it when a task matches its description.
Can I use Tlx Amd Testing in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add facebookexperimental/triton --skill tlx-amd-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/tlx-amd-testing, .gemini/skills/tlx-amd-testing, .github/skills/tlx-amd-testing and .opencode/skills/tlx-amd-testing in your project.
What does Tlx Amd Testing need to run?
Going by SKILL.md and its folder, Tlx Amd Testing needs the command-line tools its instructions call (pytest and make). Our summary lists: Python 3.
Does Tlx Amd Testing access the network?
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.
Is Tlx Amd Testing safe to install?
Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Tlx Amd Testing use?
Tlx Amd Testing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Tlx Amd Testing use?
About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Tlx Amd Testing?
Skills that share tags, products or a category with Tlx Amd Testing: Kernel Organization (sgl-project/sglang, 37k stars), Add Sgl Kernel (sgl-project/sglang, 37k stars), Add Jit Kernel (sgl-project/sglang, 37k stars) and Metal Kernel (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tlx Amd Testing?
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 9, 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.