Quark Install

What it does

When your agent uses it

• The user needs Quark package installation
• Dependency setup
• Post-install verification — after PyTorch is already set up
• Pip install amd-quark

Example prompts

• “install Quark”
• “set up Quark”
• “pip install amd-quark”
• “/quark-install”

Requirements

• Python 3
• Docker

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Intake: Determine what the user already has installed and what they need. Check if quark-torch-install has already run and PyTorch is…
2. 2Plan: Present the installation plan as a numbered sequence of commands, with version justifications.
3. 3Confirm: Required before any package installation. Show: what will be installed and what environment will be modified.
4. 4Execute: Run the installation commands.
5. 5Verify: Run all verification commands. Report pass/fail for each.

What it can do on your machine

Read from SKILL.md and the folder at commit 313cb0b. 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:

  • pip
  • git
  • python
  • docker
  • apt

  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:

  • pypi.amd.com

  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

Quark Install loads about 1.8k tokens when it runs. Until then it costs about 145 tokens; SKILL.md has 584 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~145

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

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

• NoteRuns commands with sudoSKILL.md:108

  - **Linux**: `sudo apt install build-essential` (includes g++, needed for kernel compilation)

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 amd/Quark at commit 313cb0b, republished under its MIT licence (© amd). 584 words, ~1,791 tokens.

name

quark-install

description

Install or verify the AMD Quark package and its dependencies. Use when the user needs Quark package installation, dependency setup, or post-install verification — after PyTorch is already set up. Trigger for "install Quark", "set up Quark", "pip install amd-quark", "install the Quark package", dependency errors, import failures for quark modules, or any request to get Quark running. Also trigger when the user reports ModuleNotFoundError for quark or missing C++ compiler errors. For PyTorch installation or torch version issues, use quark-torch-install instead.

layer

l1-atomic

primary_artifact

quark_install_result.json

source_knowledge

docs/source/install.rst, requirements.txt, examples/torch/language_modeling/llm_ptq/requirements.txt

{
  "status": "ok",
  "quark_version": "0.12",
  "install_source": "pypi",
  "extras_installed": {
    "onnxruntime": false,
    "llm_ptq_deps": true
  },
  "verification": {
    "import_ok": true,
    "kernel_ok": true,
    "onnx_ops_ok": null
  }
}

pip install accelerate datasets evaluate>=0.4.0 gguf>=0.10.0 lm-eval transformers<5.3

evaluate, joblib, ninja, numpy>=2.0, onnx>=1.21.0,<=1.22.0, onnxscript,
onnxslim>=0.1.84, pandas, plotly, protobuf, psutil, pydantic, rich, scipy,
sentencepiece, tqdm, zstandard

# Basic import
python -c "import quark; print('Quark version:', quark.__version__)"

# Optional: kernel compilation test
python -c "import quark.torch.kernel; print('Kernel compilation OK')"

# Optional: ONNX custom ops
python -c "import quark.onnx.operators.custom_ops; print('ONNX custom ops OK')"

docker build -f tools/ci/docker/images/Dockerfile.cuda \
  --build-arg PYTHON_VERSION=3.13 \
  --build-arg PYTORCH_VERSION=2.10.0 \
  --build-arg ACCELERATOR_VERSION=cuda-12.6 \
  -t quark:cuda .

© amd, 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-impl/l1-atomic/shared/quark-install of amd/Quark.

Open the folder on GitHubat commit 313cb0b