Quark Torch Result Validator

What it does

When your agent uses it

• Validate quantization result
• Check quantized model output
• Verify exported weights

Example prompts

• “validate quantization result”
• “check quantized model output”
• “verify exported weights”
• “/quark-torch-result-validator”

Requirements

• Python 3

Workflow steps

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

1. 1Confirm SKILL_DIR, source_model_dir, and quantized_model_dir are available.
2. 2Run self-test to verify scripts are intact: python3 "$SKILL_DIR/run_validation.py" self-test
3. 3Execute steps in cheap-to-expensive order (4 → 1 → 3 → 2).
4. 4Collect JSON from stdout for each step; write validation_report.md.
5. 5Surface any ok: false steps with their errors and mismatches.

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

  Ships script files (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  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 Result Validator loads about 1.6k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 439 words of instructions outside code blocks.

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

~106

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

~1.6k

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). 439 words, ~1,574 tokens.

name

quark-torch-result-validator

description

Validate Quark quantization output using four lightweight checks: auxiliary file copy alignment, excluded tensor MD5 byte-identity, config.json deep comparison after stripping quantization keys, and safetensors header pattern/dtype summaries. Intended for post-export or file2file validation. Trigger for "validate quantization result", "check quantized model output", "verify exported weights".

layer

l1-atomic

primary_artifact

validation_report.md

source_knowledge

examples/torch/language_modeling/llm_ptq/quantize_quark.py, quark/torch/export/api.py

SKILL_DIR=.claude/skills-impl/l1-atomic/torch/quark-torch-result-validator

SKILL_DIR=.claude/skills-impl/l1-atomic/torch/quark-torch-result-validator
python3 "$SKILL_DIR/run_validation.py" self-test

SKILL_DIR=.claude/skills-impl/l1-atomic/torch/quark-torch-result-validator

# 4. get_fuzzy_tensor_names (cheapest — header only)
python3 "$SKILL_DIR/run_validation.py" fuzzy \
  --model-path ./quantized-model

# 1. check_auxiliary_files_copied
python3 "$SKILL_DIR/run_validation.py" auxiliary \
  --source-model-dir ./original-model --quantized-model-dir ./quantized-model \
  --ignore 'README*'

# 3. check_config_json_equal_except_quantization
python3 "$SKILL_DIR/run_validation.py" config \
  --original-config ./original-model/config.json \
  --quantized-config ./quantized-model/config.json

# 2. check_non_quantized_tensors_md5_unchanged (most expensive)
python3 "$SKILL_DIR/run_validation.py" md5 \
  --source-model-dir ./original-model --output-model-dir ./quantized-model \
  --quant-config '{"exclude":["*.lm_head.weight"],"max_samples":50}'

from quant_validation import (
    check_auxiliary_files_copied,
    check_non_quantized_tensors_md5_unchanged,
    check_config_json_equal_except_quantization,
    get_fuzzy_tensor_names,
)

## Validation Report — quark-torch-result-validator

**Step 4 — fuzzy tensor names**: ok / FAIL / skipped
  - patterns: <count>, mixed-dtype patterns: <count>
  - Notable: <pattern> → <dtype_counts>

**Step 1 — auxiliary files**: ok / FAIL / skipped
  - missing: <count>, mismatched: <count>, extra: <count>

**Step 3 — config.json**: ok / FAIL / skipped
  - mismatches: <count>
  - <key>: <source_value> / <quantized_value>

**Step 2 — MD5 spot-check**: ok / FAIL / skipped
  - candidates: <count>, checked: <count>, sampled: true/false
  - mismatches: <count>

© 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

SKILL.md and 2 other files in .claude/skills-impl/l1-atomic/torch/quark-torch-result-validator of amd/Quark.

• SKILL.md
• quant_validation.py
• run_validation.py

Open the folder on GitHubat commit 313cb0b