New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Torch Profiling Tilelang Programs

by sablin39 in sablin39/tilelang-cuda-skills

Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations.

No licenceAuto-check passedAI & LLM Engineering

Install Torch Profiling Tilelang Programs

skills CLI
$ npx skills add sablin39/tilelang-cuda-skills --skill torch-profiling-tilelang-programs -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sablin39/tilelang-cuda-skills torch-profiling-tilelang-programs --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sablin39/tilelang-cuda-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tilelang/torch-profiling-tilelang-programs .claude/skills/torch-profiling-tilelang-programs && rm -rf skills-src

Use ~/.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/

Facts

Skill name
torch-profiling-tilelang-programs
GitHub stars
144
Token cost
~1.3k tokens
SKILL.md length
417 words
Files
5 (incl. scripts, references)
Skills in repo
10
Repo updated
First seen
Licence
None found

At a glance

Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations.

  • Baseline analysis and attribution
  • SKILL.md covers Understand the baseline before…, Profile a warmed workflow, Training or multi-step workflows and Allocation inspection, plus 2 more sections
  • Runs Python scripts from its folder; reaches ui.perfetto.dev and pytorch.org
  • Use dobench for controlled latency comparisons

What it does

Torch Profiling Tilelang Programs is an agent skill from sablin39/tilelang-cuda-skills. Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations. Use for baseline analysis and attribution; use dobench for controlled latency comparisons.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/bottleneck-classification.md`, `references/torch-compile-inspection.md` and `references/trace-reading-guide.md`).

It sits in AI & LLM Engineering, covering Deep learning and Performance optimization. It works with PyTorch. The repository describes itself as: Skills for writing tilelang and debugging with CUDA toolkits.

When your agent uses it

  • Baseline analysis and attribution
  • Use dobench for controlled latency comparisons

Example prompts

  • “/torch-profiling-tilelang-programs”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 502a514. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • ui.perfetto.dev
    • pytorch.org

    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

Torch Profiling Tilelang Programs loads about 1.3k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 81 tokens; SKILL.md has 417 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

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 passed

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 417 words (~1,296 tokens).

“Use torch.profiler to attribute CPU/device work and inspect scheduling, copies, allocations, and synchronization. It does not directly establish an instruction-level bottleneck. Verify CUDA profiling support in the installed build; a CPU-only trace is insufficient for GPU timing.”

— opening of SKILL.md by sablin39
name
torch-profiling-tilelang-programs

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (scripts, references) in skills/tilelang/torch-profiling-tilelang-programs of sablin39/tilelang-cuda-skills.

  • SKILL.md
  • references/bottleneck-classification.md
  • references/torch-compile-inspection.md
  • references/trace-reading-guide.md
  • scripts/profile_template.py

Open the folder on GitHubat commit 502a514

Compare with similar skills

Torch Profiling Tilelang Programs 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.

Torch Profiling Tilelang Programs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Torch Profiling Tilelang Programs this skillsablin39/tilelang-cuda-skills144—~1.3kAutomated safety check: PassNone
MUSA GPU Training Optimizeropen-infra-skills/infra-skills141—~1.7kAutomated safety check: PassApache-2.0
Tracelens Analysis Orchestratoramd/skills395—~760Automated safety check: PassMIT
The Art of Debuggingstas00/the-art-of-debugging1.7k—~6.1kAutomated safety check: NotesCC-BY-SA-4.0
Graphsignalgraphsignal/graphsignal257—~6.2kAutomated safety check: PassApache-2.0
Magpie Kernel Evaluatoramd/skills395—~2.3kAutomated safety check: PassMIT

Similar skills

  • MUSA GPU Training Optimizer

    open-infra-skills/infra-skills

    Profiles, benchmarks and tunes AI training workloads on Moore Threads MUSA GPUs with a measurement-first process that keeps model behavior unchanged.

    141 GitHub stars~1.7k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

  • Tracelens Analysis Orchestrator

    amd/skills

    Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs…

    395 GitHub stars~760 tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • The Art of Debugging

    stas00/the-art-of-debugging

    Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.

    1.7k GitHub stars~6.1k tokensUpdated yesterday
    DevelopmentAuto-check: notes

  • Graphsignal

    graphsignal/graphsignal

    Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

    257 GitHub stars~6.2k tokensUpdated 9 days ago
    AI & LLM EngineeringAuto-check passed

  • Magpie Kernel Evaluator

    amd/skills

    Benchmarks LLM inference and drives GPU kernel optimization with Magpie.

    395 GitHub stars~2.3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Torch Performance Optimization

    albumentations-team/albucore

    Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.

    123 GitHub stars~895 tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed

More from sablin39/tilelang-cuda-skills

All 10 skills in this repo

  • Writing Tilelang Design Docs

    sablin39/tilelang-cuda-skills

    Write human-facing TileLang design documents for proposed or completed kernel implementations.

    144 GitHub stars~2.2k tokensUpdated 22 days ago
    Auto-check passed

  • Cuda

    sablin39/tilelang-cuda-skills

    Draft, debug, and measure CUDA kernels and host launch workflows.

    144 GitHub stars~990 tokensUpdated 22 days ago
    Auto-check passed

  • Debugging Tilelang Programs

    sablin39/tilelang-cuda-skills

    Diagnose TileLang compilation, host argument, memory-liveness, runtime, and numerical failures.

    144 GitHub stars~1.6k tokensUpdated 22 days ago
    Auto-check passed

  • Designing With Tilefoundry

    sablin39/tilelang-cuda-skills

    Describe model or operator HIR with TileFoundry, inspect topology and placement, run static cost analysis, visualize authored dataflow, and check a runtime implementation against its evaluator.

    144 GitHub stars~3.4k tokensUpdated 22 days ago
    Auto-check passed

  • Profiling Tilelang Programs

    sablin39/tilelang-cuda-skills

    Measure TileLang kernel and workflow performance, choose benchmark or timeline tools, and compare implementations fairly.

    144 GitHub stars~1.6k tokensUpdated 22 days ago
    Auto-check passed

  • Optimizing Tilelang Programs

    sablin39/tilelang-cuda-skills

    Tune a correct TileLang kernel using measured bottlenecks, tile sizes, layouts, pipelining, fusion, and autotuning.

    144 GitHub stars~1k tokensUpdated 22 days ago
    Auto-check passed

Works with

Categories

Questions about Torch Profiling Tilelang Programs

What does Torch Profiling Tilelang Programs do?

Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations. Torch Profiling Tilelang Programs is an agent skill from sablin39/tilelang-cuda-skills.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations.

When should I use Torch Profiling Tilelang Programs?

Torch Profiling Tilelang Programs fits situations like: baseline analysis and attribution; use dobench for controlled latency comparisons.

How do I install Torch Profiling Tilelang Programs in Claude Code?

Run `npx skills add sablin39/tilelang-cuda-skills --skill torch-profiling-tilelang-programs -a claude-code`. Or copy the skill folder (skills/tilelang/torch-profiling-tilelang-programs in sablin39/tilelang-cuda-skills) into .claude/skills/torch-profiling-tilelang-programs in your project. Claude Code loads it when a task matches its description.

How do I install Torch Profiling Tilelang Programs in Codex?

Run `npx skills add sablin39/tilelang-cuda-skills --skill torch-profiling-tilelang-programs -a codex`. Or copy the skill folder (skills/tilelang/torch-profiling-tilelang-programs in sablin39/tilelang-cuda-skills) into .agents/skills/torch-profiling-tilelang-programs in your project. Codex loads it when a task matches its description.

Can I use Torch Profiling Tilelang Programs 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 sablin39/tilelang-cuda-skills --skill torch-profiling-tilelang-programs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/torch-profiling-tilelang-programs, .gemini/skills/torch-profiling-tilelang-programs, .github/skills/torch-profiling-tilelang-programs and .opencode/skills/torch-profiling-tilelang-programs in your project.

What does Torch Profiling Tilelang Programs need to run?

Going by SKILL.md and its folder, Torch Profiling Tilelang Programs needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Torch Profiling Tilelang Programs access the network?

SKILL.md names 2 domains. In commands or code: ui.perfetto.dev and pytorch.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Torch Profiling Tilelang Programs safe to install?

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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Torch Profiling Tilelang Programs use?

No licence was found for Torch Profiling Tilelang Programs or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Torch Profiling Tilelang Programs use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.

What are the alternatives to Torch Profiling Tilelang Programs?

Skills that share tags, products or a category with Torch Profiling Tilelang Programs: MUSA GPU Training Optimizer (open-infra-skills/infra-skills, 141 stars), Tracelens Analysis Orchestrator (amd/skills, 395 stars), The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars) and Graphsignal (graphsignal/graphsignal, 257 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Torch Profiling Tilelang Programs?

sablin39 (a GitHub user) maintains it in sablin39/tilelang-cuda-skills, which has 144 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 15, 2026.

Source: sablin39/tilelang-cuda-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.