Quark Onnx Result Validator

What it does

When your agent uses it

• Validate ONNX quantization result
• Check quantized .onnx output
• Verify ONNX initializers
• Did QDQ insertion happen

Example prompts

• “validate ONNX quantization result”
• “check quantized .onnx output”
• “verify ONNX initializers”
• “/quark-onnx-result-validator”

Requirements

• Python 3

Workflow steps

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

1. 1Confirm SKILL_DIR, source_model_path (if available), and quantized_model_path are
2. 2Run the self-test to verify scripts are intact
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 / 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 Onnx Result Validator loads about 2.5k tokens when it runs. Until then it costs about 175 tokens; SKILL.md has 766 words of instructions outside code blocks.

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

~175

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

~2.5k

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). 766 words, ~2,534 tokens.

name

quark-onnx-result-validator

description

Validate Quark ONNX quantization output using four lightweight checks: auxiliary file copy alignment, expected non-quantized initializer MD5 byte-identity (inline `raw_data` + external-data byte ranges), model metadata equality after stripping quantization-only opset entries / Quark domains, and fuzzy node-pattern + op-type + dtype summaries with QDQ / `com.amd.quark` custom-op presence. Intended for post-quantization inspection of `model.onnx` (with or without `model.onnx_data`). Trigger for "validate ONNX quantization result", "check quantized .onnx output", "verify ONNX initializers", "did QDQ insertion happen", "are the non-quantized weights byte-identical".

layer

l1-atomic

primary_artifact

validation_report.md

source_knowledge

examples/onnx/yolo_quantization/quantize_yolo.py, examples/onnx/language_models/opt/quantize_model.py…

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

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

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

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

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

# 3. check_model_metadata_equal_except_quantization
python3 "$SKILL_DIR/run_validation.py" metadata \
  --source-model-path ./source/model.onnx \
  --quantized-model-path ./quantized/model.onnx

# 2. check_non_quantized_initializers_md5_unchanged (most expensive)
python3 "$SKILL_DIR/run_validation.py" md5 \
  --source-model-path ./source/model.onnx \
  --output-model-path ./quantized/model.onnx \
  --quant-config '{"exclude":["*.bias","embeddings.*.weight"],"max_samples":50}'

from quant_validation_onnx import (
    check_auxiliary_files_copied,
    check_non_quantized_initializers_md5_unchanged,
    check_model_metadata_equal_except_quantization,
    get_fuzzy_node_op_summary,
)

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

**Step 4 — fuzzy node / op summary**: ok / FAIL / skipped
  - op types: <count>, QDQ nodes: <count>, com.amd.quark nodes: <count>
  - Notable: <pattern> → <op_type_counts>
  - Quantization signal: present / **MISSING** / partial

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

**Step 3 — model metadata**: ok / FAIL / skipped
  - ir_version: <source> / <quantized>
  - opset_import (default domain): <source> / <quantized>
  - input/output signature diffs: <count>
  - Quark-injected opset domains: <list>

**Step 2 — MD5 spot-check (initializers)**: ok / FAIL / skipped
  - candidates: <count>, checked: <count>, sampled: true/false
  - mismatches: <count>
  - external_data_missing: <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/onnx/quark-onnx-result-validator of amd/Quark.

• SKILL.md
• quant_validation_onnx.py
• run_validation.py

Open the folder on GitHubat commit 313cb0b