ptq-workflow-integration

ptq-workflow-integration is a skill for Claude Code, Codex from vipshop/cache-dit. It costs 75 tokens per session (2,380 once invoked), scanned A, original, Apache-2.0.

A workflow guide for adding post-training quantization (reducing a trained model’s size or compute needs) to the cache-dit project. It covers public interfaces, backend-specific settings, saved metadata, tests, benchmarks, and documentation.

In plain words
What is it for?
Use it when adding or reviewing a quantization backend, designing its quantize and load interfaces, validating settings, saving or loading model files, and planning tests or benchmarks.
Why use it?
It helps keep a new quantization method consistent with the project while avoiding copied code that may not fit. It also separates quick checks from slower performance and regression tests.

Skill for Claude CodeCodex

About the project

Cache-DiT is a PyTorch inference engine for DiT models, with caching, parallel processing, quantization, and CPU offloading. It is for running diffusion-model pipelines with support for systems and hardware such as Diffusers, SGLang Diffusion, vLLM-Omni, ComfyUI, NVIDIA GPUs, Ascend NPUs, and AMD GPUs.

vipshop/cache-dit · 1,270 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/vipshop/cache-dit/ptq-workflow-integration
Any agent
npx skills add vipshop/cache-dit --skill ptq-workflow-integration
Clone the repo
git clone --depth 1 https://github.com/vipshop/cache-dit

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ptq-workflow-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/vipshop/cache-dit/ptq-workflow-integration.svg)](https://agentmods.dev/skills/vipshop/cache-dit/ptq-workflow-integration)
Your own site
<a href="https://agentmods.dev/skills/vipshop/cache-dit/ptq-workflow-integration"><img src="https://agentmods.dev/badge/skills/vipshop/cache-dit/ptq-workflow-integration.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.02380
Opus 5 $0.00037 $0.01190
Sonnet 5 $0.00015 $0.00476
Haiku 4.5 $0.00007 $0.00238

Measured 5d ago against content hash 323f68112017, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ptq-workflow-integration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/skills/ptq-workflow-integration/SKILL.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PTQ Workflow Integration for cache-dit

Goal

Integrate one PTQ workflow in a way that feels native to cache-dit:

  • public API stays simple
  • backend-specific logic stays localized
  • save/load UX is predictable
  • fast tests and slow tests cover different risks
  • docs show only the public workflow

This skill is based on lessons from the SVDQ PTQ integration, but SVDQ PTQ is a reference only.

Core Rule

Do not mechanically copy SVDQ PTQ files.

Use the SVDQ PTQ integration to learn:

  • what belongs in public API vs private backend code
  • where config validation should live
  • where backend serialization and load logic should live
  • how tests should be split by cost and purpose
  • what documentation shape is acceptable for cache-dit

Do not reuse SVDQ PTQ by blind copy-paste.

Specifically do not copy without redesigning first:

  • private helper structure
  • class names or helper names
  • logging layout
  • exact file decomposition
  • prompts, thresholds, or benchmark constants
  • test bodies that only happen to fit SVDQ

Treat SVDQ as a style reference, not a template to replay.

When to Use

Use this skill when you need to:

  • add a new PTQ backend or algorithm into cache-dit
  • extend an existing PTQ backend with save/load support
  • decide where PTQ files and tests should live
  • review whether a PTQ integration follows cache-dit API style
  • plan coverage for a PTQ feature before coding

Do not use this skill for:

  • generic quantization work that does not involve PTQ workflow design
  • blind upstream porting
  • one-off benchmark scripts with no repository integration

Reference Style Rule

Use repo-relative references only.

  • For cache-dit files, use paths like src/cache_dit/quantization/config.py.
  • For docs, use paths like docs/user_guide/QUANTIZATION.md.
  • For tests, use paths like tests/quantization/test_svdquant_ptq.py.
  • Do not write machine-local absolute paths into the skill.

Design Principles to Keep

1. Public API symmetry matters

Prefer a user-facing flow like:

Read the full file on GitHub · 296 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 296 lines · 75 tokens per session scan A 323f68112017

Subscribe to this mod's changes

ptq-workflow-integration is a skill published in the GitHub repository vipshop/cache-dit (1,270 stars, last pushed 2d ago), licensed Apache-2.0. It adds 75 tokens to every session and 2,380 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens