Quark Torch Quant Plan

What it does

When your agent uses it

• The user needs quantization scheme recommendations
• Exclusion lists
• Algorithm selection
• KV cache decisions

Example prompts

• “quantize with FP8”
• “what scheme should I use”
• “plan PTQ”
• “/quark-torch-quant-plan”

Workflow steps

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

1. 1Check prerequisites: Is model_analysis.json available? If not, route to quark-torch-model-intake first.
2. 2Gather intent: What does the user care about most — accuracy, size, speed? What hardware will run inference?
3. 3Present the decision table: Show defaults, explain the tradeoffs, and let the user adjust.
4. 4Confirm: Always required. Show the final plan summary before writing it.
5. 5Emit: Write quant_plan.json.

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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json and bash).

  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

Quark Torch Quant Plan loads about 2.3k tokens when it runs. Until then it costs about 123 tokens; SKILL.md has 905 words of instructions outside code blocks.

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

~123

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

~2.3k

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

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). 905 words, ~2,284 tokens.

name

quark-torch-quant-plan

description

Build a Quark Torch LLM PTQ quantization plan from model analysis and user intent. Use when the user needs quantization scheme recommendations, exclusion lists, algorithm selection, KV cache decisions, per-layer overrides, or a draft quant_plan. Trigger for "quantize with FP8", "what scheme should I use", "plan PTQ", "INT4 quantization", "choose quantization config", "quantization plan", or when the user has a model analysis and needs to decide how to quantize it.

layer

l1-atomic

primary_artifact

quant_plan.json

source_knowledge

quark/torch/quantization/config/template.py, examples/torch/language_modeling/llm_ptq/README.md, examples/torch/language_modeling/llm_ptq/quantize_quark.py

{
  "model": {
    "model_type": "qwen3",
    "analysis_ref": "./model_analysis.json"
  },
  "global_scheme": "fp8",
  "kv_cache_scheme": "fp8",
  "exclude_layers": ["lm_head"],
  "layer_quant_config": {},
  "algorithm": null,
  "calibration": {
    "dataset": "pileval",
    "num_calib_data": 128,
    "seq_len": 512
  },
  "evaluation_intent": "smoke",
  "requires_confirmation": false
}

"layer_quant_config": {
  "*self_attn*": "fp8",
  "lm_head": "int8",
  "*experts*": "fp8"
}

--quant_scheme <global_scheme> \
--layer_quant_scheme '*self_attn*' fp8 \
--layer_quant_scheme lm_head int8 \
--layer_quant_scheme '*experts*' fp8

© 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/torch/quark-torch-quant-plan of amd/Quark.

Open the folder on GitHubat commit 313cb0b