Aider Delegate
amElnagdy/delegate-skills
Delegate a coding task to Aider (aider) as a background implementer, then review its diff and land it yourself.
Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models.
Install Quantization
$ npx skills add vllm-project/vllm-omni --skill quantization -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install vllm-project/vllm-omni quantization --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/vllm-project/vllm-omni.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/quantization .claude/skills/quantization && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "quantization" agent skill from https://github.com/vllm-project/vllm-omni/tree/main/.claude/skills/quantization into .claude/skills/quantization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantization", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/vllm-project/vllm-omni/tree/main/.claude/skills/quantizationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add vllm-project/vllm-omni --skill quantization -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install vllm-project/vllm-omni quantization --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vllm-project/vllm-omni.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/quantization .agents/skills/quantization && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "quantization" agent skill from https://github.com/vllm-project/vllm-omni/tree/main/.claude/skills/quantization into .agents/skills/quantization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantization", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vllm-project/vllm-omni --skill quantization -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install vllm-project/vllm-omni quantization --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vllm-project/vllm-omni.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/quantization .cursor/skills/quantization && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "quantization" agent skill from https://github.com/vllm-project/vllm-omni/tree/main/.claude/skills/quantization into .cursor/skills/quantization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantization", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/vllm-project/vllm-omni.git --path .claude/skills/quantization--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add vllm-project/vllm-omni --skill quantization -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install vllm-project/vllm-omni quantization --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vllm-project/vllm-omni.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/quantization .gemini/skills/quantization && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "quantization" agent skill from https://github.com/vllm-project/vllm-omni/tree/main/.claude/skills/quantization into .gemini/skills/quantization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantization", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install vllm-project/vllm-omni quantizationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add vllm-project/vllm-omni --skill quantization -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/vllm-project/vllm-omni.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/quantization .github/skills/quantization && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "quantization" agent skill from https://github.com/vllm-project/vllm-omni/tree/main/.claude/skills/quantization into .github/skills/quantization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantization", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add vllm-project/vllm-omni --skill quantization -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install vllm-project/vllm-omni quantization --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vllm-project/vllm-omni.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/quantization .opencode/skills/quantization && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "quantization" agent skill from https://github.com/vllm-project/vllm-omni/tree/main/.claude/skills/quantization into .opencode/skills/quantization/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantization", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
quantization- GitHub stars
- 7.1k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 560 words
- Files
- 6 (incl. references)
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models.
- Works in 6 steps: Read the local method doc under… → Inspect the active factory and config… → Inspect the target model pipeline and… → …
- Adding methods such as fp8
- SKILL.md covers First Checks, Quick Decision, Current Runtime Shape and Ownership Boundary, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Quantization is an agent skill from vllm-project/vllm-omni. Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models. Use when choosing or adding methods such as fp8, int8, gguf, mxfp8, mxfp4, mxfp4dualscale, ModelOpt, AutoRound, INC, msModelSlim, awq, or gptq; debugging quantized loading; or validating memory, speed, and output quality.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/adding-models.md`, `references/diffusion.md` and `references/methods.md`).
It sits in AI & LLM Engineering, covering LLM inference and serving. It works with vLLM and llama.cpp. The repository describes itself as: A framework for efficient model inference with omni-modality models. The licence is Apache-2.0.
When your agent uses it
- Adding methods such as fp8
- Debugging quantized loading
- Validating memory
Example prompts
- “/quantization”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Read the local method doc under docs/user_guide/quantization/.
- Inspect the active factory and config class in vllm_omni/quantization/.
- Inspect the target model pipeline and transformer for stable prefixes and
- For pre-quantized checkpoints, inspect transformer/config.json and the
- Validate with the same prompt, seed, size, scheduler, steps, dtype, eager or
- Report quality, latency, and memory separately. Do not call a method
What it can do on your machine
Read from SKILL.md and the folder at commit c548a11. 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 python).
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
Quantization loads about 1.4k tokens when it runs, and up to ~6k if it reads all its reference files. Until then it costs about 82 tokens; SKILL.md has 560 words of instructions outside code blocks.
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
Auto-check passed
The automated check found no risky patterns in SKILL.md.
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 vllm-project/vllm-omni at commit c548a11, republished under its Apache-2.0 licence (© vllm-project). 560 words, ~1,354 tokens.
Download SKILL.mdSave it as
.claude/skills/quantization/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- quantization
- description
- Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models. Use when choosing or adding methods such as fp8, int8, gguf, mxfp8, mxfp4, mxfp4_dualscale, ModelOpt, AutoRound, INC, msModelSlim, awq, or gptq; debugging quantized loading; or validating memory, speed, and output quality.
vLLM-Omni Quantization
Use this skill for quantization work in vllm-omni. Start from the local
code and docs, then pick the smallest validated path for the model, method,
hardware, and quality target.
First Checks
Before changing code or recommending a command, identify:
- Model and task: AR text, omni/TTS, text-to-image, text-to-video, or multi-stage diffusion.
- Hardware backend: CUDA generation, Ascend NPU, Intel XPU, or another platform.
- Quantization mode: online from BF16/FP16 weights, pre-quantized checkpoint, runtime KV/FA quantization, or per-component routing.
- Scope: transformer/DiT, thinker language model, text encoder, VAE, audio/vision encoder, talker, or a specific stage.
- Validation target: memory reduction, latency/throughput, output quality, or all three.
Do not assume a method is supported just because the CLI accepts the string.
Check docs/user_guide/quantization/ and the closest implementation first.
Quick Decision
| Task | Start With |
|---|---|
| Choose a method or command | references/methods.md and references/modality-compat.md |
Use build_quant_config() or per-component routing | references/methods.md |
| Work on diffusion quantization | references/diffusion.md |
| Add quantization to a new model | references/adding-models.md |
| Convert or load ModelOpt FP8 checkpoints | references/modelopt-fp8.md |
| Debug ModelOpt, GGUF, AutoRound, MXFP, or serialized Int8 loading | references/diffusion.md and method docs under docs/user_guide/quantization/ |
Current Runtime Shape
The unified entrypoint is:
from vllm_omni.quantization import build_quant_configIt supports method strings, flat method dictionaries, per-component
dictionaries, existing QuantizationConfig objects, and None. The factory
delegates generic methods to upstream vllm and keeps vLLM-Omni overrides for
diffusion or omni-specific routing:
ggufint8mxfp8mxfp4mxfp4_dualscaleinc,auto-round,auto_round- ModelOpt auto-detected configs:
modelopt,modelopt_fp4,modelopt_mixed
Use ComponentQuantizationConfig when only one stage or component should be
quantized. Pre-quantized ModelOpt-style checkpoints should not spill into
vision/audio encoders that have no corresponding scale tensors.
Ownership Boundary
- Upstream
vllmowns generic quantization configs, kernels, loader semantics, hardware capability rules, and generic AR quantization methods. vllm-omniowns unified config routing, diffusion-specific wrappers, component scoping, GGUF or ModelOpt checkpoint adapters, model-specific prefix mapping, docs, examples, and validation.
If a new method needs missing generic kernels or loader behavior, fix upstream
vllm first. In vllm-omni, add thin integration and model wiring.
Show full SKILL.md (243 more words)Show less
Working Loop
- Read the local method doc under
docs/user_guide/quantization/. - Inspect the active factory and config class in
vllm_omni/quantization/. - Inspect the target model pipeline and transformer for stable prefixes and
whether every relevant vLLM linear layer receives
quant_config. - For pre-quantized checkpoints, inspect
transformer/config.jsonand the checkpoint tensor names before running full generation. - Validate with the same prompt, seed, size, scheduler, steps, dtype, eager or non-eager mode, and parallelism as the BF16 baseline.
- Report quality, latency, and memory separately. Do not call a method supported until quality is checked.
Common Mistakes
| Symptom | Likely Cause | Fix |
|---|---|---|
--quantization has no visible effect | Wrong scope or unsupported model path | Check component routing and method docs |
| Some layers stay BF16 unexpectedly | quant_config was not threaded into all vLLM linear layers | Audit transformer constructors and prefixes |
| Quality collapses but loading succeeds | Too many sensitive layers were quantized | Add model-specific ignored_layers and compare to BF16 |
| ModelOpt checkpoint loads but output is corrupted | Prefixes, packed-module mapping, scale routing, or BF16 fallback is wrong | Use references/modelopt-fp8.md |
| GGUF shape or tensor mismatch | Missing architecture-specific adapter | Add explicit adapter mapping; avoid generic fallback |
| Online and offline MXFP4 disagree | Wrong mxfp4 vs mxfp4_dualscale mode | Check docs/user_guide/quantization/mxfp4.md |
| Quantized path is slower than BF16 | Kernel path, compile mode, dtype, or shape mismatch | Compare eager-to-eager and non-eager-to-non-eager |
References
- General methods and config routing: references/methods.md
- Modality and model scope: references/modality-compat.md
- Diffusion implementation patterns: references/diffusion.md
- Adding model support: references/adding-models.md
- ModelOpt FP8 conversion and loading: references/modelopt-fp8.md
© vllm-project, Apache-2.0. 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 5 other files (references) in .claude/skills/quantization of vllm-project/vllm-omni.
- SKILL.md
- references/adding-models.md
- references/diffusion.md
- references/methods.md
- references/modality-compat.md
- references/modelopt-fp8.md
Open the folder on GitHubat commit c548a11
Compare with similar skills
Quantization next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Quantization this skillvllm-project/vllm-omni | 7.1k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Aider DelegateamElnagdy/delegate-skills | 2.3k | 3 repos | ~3k | Automated safety check: Pass | MIT | |
| Model Serving MinefieldBlackwellboy/model-serving-minefield | 135 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Add Export Formatintel/auto-round | 1.6k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Add Modelguoqingbao/xinfer | 333 | — | ~4.2k | Automated safety check: Notes | MIT | |
| Resolvealexziskind1/model-shelf | 130 | — | ~792 | Automated safety check: Pass | MIT |
Similar skills
Model Serving Minefield
Blackwellboy/model-serving-minefield
Diagnose OpenAI-compatible model-serving failures from symptoms, endpoint reports, explicit configuration files, or logs while preserving evidence status and requiring confirm/refute checks.
- Official
Add Export Format
intel/auto-round
Add a new model export format to AutoRound (e.g., autoround, autogptq, autoawq, gguf, llmcompressor).
Add Model
guoqingbao/xinfer
Adapt and port new LLM model architectures to this xinfer project.
Resolve
alexziskind1/model-shelf
Always resolve Hugging Face models via model-shelf before any download.
Outlines Structured Generation
Orchestra-Research/AI-Research-SKILLs
Uses the Outlines library to constrain model output to a JSON schema, Pydantic model, regex or fixed set of choices when running local models.
More from vllm-project/vllm-omni
All 20 skills in this repoDiffusion Perf Opt
vllm-project/vllm-omni
Diagnose and optimize vLLM Omni diffusion workloads, especially Wan/Qwen/Flux-style image and video generation.
Precheck PR
vllm-project/vllm-omni
Self-check your branch before creating a PR — catch dead code, prevent new model-specific Python examples, verify accuracy/perf claims, validate PR title format, and confirm merge readiness.
Review PR
vllm-project/vllm-omni
Review pull requests and local branches for vllm-project/vllm-omni with a frozen snapshot, module-design ownership, feature-design overlays, targeted validation, and concise evidence-backed findings.
H3 Prompt Writing
vllm-project/vllm-omni
Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA.
Add Diffusion Model
vllm-project/vllm-omni
Add a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including native non-Diffusers ports, reference-parity validation, Cache-DiT…
Add Recipe
vllm-project/vllm-omni
Add or update an in-repository vLLM-Omni model recipe with verified task, input, output, hardware, command, feature, and validation contracts.
Related
Categories
Questions about Quantization
What does Quantization do?
Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models. Quantization is an agent skill from vllm-project/vllm-omni. Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models.
When should I use Quantization?
Quantization fits situations like: adding methods such as fp8; debugging quantized loading; validating memory.
How do I install Quantization in Claude Code?
Run `npx skills add vllm-project/vllm-omni --skill quantization -a claude-code`. Or copy the skill folder (.claude/skills/quantization in vllm-project/vllm-omni) into .claude/skills/quantization in your project. Claude Code loads it when a task matches its description.
How do I install Quantization in Codex?
Run `npx skills add vllm-project/vllm-omni --skill quantization -a codex`. Or copy the skill folder (.claude/skills/quantization in vllm-project/vllm-omni) into .agents/skills/quantization in your project. Codex loads it when a task matches its description.
Can I use Quantization in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vllm-project/vllm-omni --skill quantization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/quantization, .gemini/skills/quantization, .github/skills/quantization and .opencode/skills/quantization in your project.
What does Quantization need to run?
SKILL.md names no scripts, command-line tools or credentials: Quantization is instructions for the agent only. Our summary lists: Python 3.
Does Quantization access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Quantization safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Quantization use?
Quantization is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Quantization use?
About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.7k tokens, read only when the agent opens those files.
What are the alternatives to Quantization?
Skills that share tags, products or a category with Quantization: Aider Delegate (amElnagdy/delegate-skills, 2.3k stars), Model Serving Minefield (Blackwellboy/model-serving-minefield, 135 stars), Add Export Format (intel/auto-round, 1.6k stars) and Add Model (guoqingbao/xinfer, 333 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Quantization?
vllm-project (a GitHub organization) maintains it in vllm-project/vllm-omni, which has 7,072 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.
Source: vllm-project/vllm-omni on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.