Agent skill

Vllm Metax Registry Upgrade

by MetaX-MACA in MetaX-MACA/vLLM-metax

Review and adapt vllmmetax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Vllm Metax Registry Upgrade

skills CLI
$ npx skills add MetaX-MACA/vLLM-metax --skill vllm-metax-registry-upgrade -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install MetaX-MACA/vLLM-metax vllm-metax-registry-upgrade --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/MetaX-MACA/vLLM-metax.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/vllm-metax-registry-upgrade .claude/skills/vllm-metax-registry-upgrade && rm -rf skills-src

Use ~/.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/

Facts

Skill name
vllm-metax-registry-upgrade
GitHub stars
180
Token cost
~1.8k tokens
SKILL.md length
825 words
Files
4 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

Review and adapt vllmmetax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs.

  • Registry compatibility work
  • SKILL.md covers Scope and environment, Trace registration and dispatch, Verify semantics and adapt and Validate and report
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Not standalone attention algorithms

What it does

Vllm Metax Registry Upgrade is an agent skill from MetaX-MACA/vLLM-metax. Review and adapt vllmmetax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs. Verify registration, inherited state, weight layouts and actual backend selection. Use for registry compatibility work, not standalone attention algorithms or monkey patches.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/quantization-contracts.md` and `references/validation.md`).

It sits in AI & LLM Engineering, covering LLM inference and serving. It works with vLLM. The repository describes itself as: Community maintained hardware plugin for vLLM on MetaX GPU. The licence is Apache-2.0.

When your agent uses it

  • Registry compatibility work
  • Not standalone attention algorithms

Example prompts

  • “/vllm-metax-registry-upgrade”

What it can do on your machine

Read from SKILL.md and the folder at commit df0f52b. 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.

    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

Vllm Metax Registry Upgrade loads about 1.8k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 825 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

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 MetaX-MACA/vLLM-metax at commit df0f52b, republished under its Apache-2.0 licence (© MetaX-MACA). 825 words, ~1,795 tokens.

Download SKILL.mdSave it as .claude/skills/vllm-metax-registry-upgrade/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
vllm-metax-registry-upgrade
description
Review and adapt vllm_metax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs. Verify registration, inherited state, weight layouts and actual backend selection. Use for registry compatibility work, not standalone attention algorithms or monkey patches.

vLLM-MetaX Registry Upgrade

Maintain the full contract from plugin activation to the selected implementation. A registered class name, matching signature, or upstream support declaration does not establish that the installed MetaX implementation supports the same behavior.

Scope and environment

  • Apply to requested adaptations in vllm_metax/registry/, including quantization configurations, CustomOps and linear kernels. Inspect directly related oracles, experts, wrappers and callers outside that directory as necessary. Edit them only when needed for the authorized adaptation; do not expand into unrelated changes.
  • For sparse indexers registered here, cover registration, constructor compatibility, dtype dispatch and wrapper contracts. Standalone attention algorithm, cache-index or numerical kernel work belongs to the attention workflow. Monkey patches belong to the patch workflow. Do not automatically invoke either skill, impose patch headers, or write registry findings into vllm_metax/patch/AUDIT.md.
  • Keep review-only requests read-only. Identify the subject: staged snapshot, working tree, installed package or specified revision. Preserve user changes and do not stage, commit, reinstall packages or edit upstream/site-packages without authorization. For staged validation, export the index and prove that imports use that snapshot; unstaged files must not silently supply missing staged dependencies.
  • Read applicable repository instructions.
  • Read and apply vllm-metax-upgrade-common before compatibility decisions. It owns environment/source discovery, the shared read-only probe, one-time target confirmation and verification evidence rules. Reuse the same established environment record across upgrade skills; do not ask again for an unchanged mapping. Keep the domain-specific workflow below.

Trace registration and dispatch

Inventory every requested registration, including inactive/conditional entries and aggregate import files. Record the registry key or target, activation path, effective class/callable, upstream counterpart, MetaX difference, decision and evidence.

Trace the actual chain:

text
plugin entry point -> package imports -> decorator/table mutation
-> config lookup or CustomOp/platform dispatch -> selected method
-> backend oracle -> experts/prepare-finalize -> wrapper -> installed kernel
  • Exercise fresh-process plugin startup as well as direct module imports. One missing symbol in an eagerly imported quantization module can break every registration. A partially populated registry after an exception is not successful startup.
  • Resolve aliases, lazy exports, module redirects, duplicate keys and import ordering. Verify the effective lookup result and caller binding, not only decorator presence.
  • Check exact platform keys (including OOT), dtype/capability predicates and explicit backend overrides. Preserve other platforms' entries and explicit user choices.
  • For overridden classes, inspect the current MRO and inherited methods. A copied constructor's super() may now call a parent with a different signature. Bypassing that parent requires initializing all state consumed by inherited allocation, loading, quant-config and execution methods.
  • Check actual factory signatures and return contracts. Follow the selected class's module/source through kernel invocation. A MetaX-named oracle can still return upstream experts and bypass MCOPLIB, local tuning or communication adaptations, which could lead to potential errors.
  • Distinguish shared and separately defined enums. Matching member names or values do not make members of different Enum classes interchangeable in backend dispatch.
Show full SKILL.md (383 more words)Show less

Verify semantics and adapt

For quantization work, read quantization-contracts.md. For CustomOps and linear registrations, apply the same chain checks to real/fake schemas, optional inputs, tensor/tuple outputs, layout requirements and capability predicates.

Choose per entry: retain a needed difference, update the adapter, remove redundant code, migrate to a supported extension point, or reject an unsupported combination early. Do not copy upstream support claims into MetaX predicates without checking the installed implementation. Comments and earlier review conclusions are hypotheses to verify.

  • Validate joint configurations: quantization format, symmetry, group size, activation, bias, device, parallel mode and selected backend. Supporting one dimension does not establish support for every combination.
  • Keep allocation, checkpoint loading, post-load conversion, parameter replacement, quant-config construction and kernel consumption consistent. Returned converted tensors must actually reach the kernel through the layer/config used by execution.
  • Keep MetaX-specific behavior only where justified. Removing a redundant override is valid when the inherited implementation and its dependencies provide the same behavior.
  • Preserve algorithm and layout explanations. State dimension meanings, packing axes, stride requirements, conversion order and why the MetaX path differs. Do not impose monkey-patch headers on registry files.
  • Attribute defects carefully: new adapter regression, existing adapter defect, target upstream defect, installed component bug or environment mismatch. To claim an upstream defect, inspect and reproduce the actual target path; limit the claim to that revision.

Validate and report

Read validation.md and select checks that discriminate the changed behavior, using the common skill's isolated-validation and evidence rules.

Start with startup/lookup and interface checks, then validate affected state/layout and real GPU behavior. An isolated constructor or scatter test may bypass an earlier failure inside that test process, but record the bypass and keep the real function under review. Such tests do not establish production reachability or kernel support.

For a re-review, account for every prior finding as fixed, partially fixed, still present, or masked by an earlier failure/capability rejection. Do not stop after fixing the first exception. A rejected asymmetric configuration can hide a broken zero-point scatter.

Report locations, trigger, consequence, evidence, verification level and untested scope. For fixes, include what changed, actual interpreter/import origins and reproducible test commands/results. Record runtime workarounds explicitly. Do not claim full-model, distributed, capture or performance validation from import and tensor-layout checks. Use a user-requested audit location if provided; no separate audit file is mandatory.

© MetaX-MACA, 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 3 other files (references) in .codex/skills/vllm-metax-registry-upgrade of MetaX-MACA/vLLM-metax.

  • SKILL.md
  • agents/openai.yaml
  • references/quantization-contracts.md
  • references/validation.md

Open the folder on GitHubat commit df0f52b

Compare with similar skills

Vllm Metax Registry Upgrade 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.

Vllm Metax Registry Upgrade compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vllm Metax Registry Upgrade this skillMetaX-MACA/vLLM-metax180—~1.8kAutomated safety check: PassApache-2.0
SageMaker Serving Image Selectionhuggingface/skills11k1 repos~4.6kAutomated safety check: PassApache-2.0
Hugging Face Local Model Evalshuggingface/skills11k2 repos~1.6kAutomated safety check: PassApache-2.0
CI Fails Buildkiteguqiong96/Lvllm4652 repos~349Automated safety check: PassApache-2.0
Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel1.3k—~1.1kAutomated safety check: PassCustom licence
Add Diffusion Modelvllm-project/vllm-omni7.1k—~7kAutomated safety check: PassApache-2.0

Similar skills

  • Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed
  • Official

    Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

    11k GitHub starsUsed in 2 repos~1.6k tokens
    AI & LLM EngineeringAuto-check passed
  • CI Fails Buildkite

    guqiong96/Lvllm

    Fetch and diagnose vLLM Buildkite CI failure logs. An agent skill from guqiong96/Lvllm.

    465 GitHub starsUsed in 2 repos~349 tokens
    AI & LLM EngineeringAuto-check passed
  • Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.

    1.3k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • 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…

    7.1k GitHub stars~7k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • 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.

    7.1k GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from MetaX-MACA/vLLM-metax

  • Vllm Metax Model Upgrade

    MetaX-MACA/vLLM-metax

    Review and upgrade MetaX model support against a target vLLM revision and installed MACA components, recursively including model-dependent attention and kernels.

    180 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed
  • Vllm Metax Attention Upgrade

    MetaX-MACA/vLLM-metax

    Review and adapt MetaX attention backends, MLA, sparse indexers, cache layouts, and their kernel wrappers against a target vLLM revision and the actually installed MetaX component APIs.

    180 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed
  • Vllm Metax Patch Upgrade

    MetaX-MACA/vLLM-metax

    Audit and adapt monkey patches in vllmmetax/patch/ against a target upstream revision.

    180 GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed
  • Vllm Metax Upgrade Common

    MetaX-MACA/vLLM-metax

    Establish the shared environment, source/runtime correspondence, target confirmation and validation evidence for MetaX vLLM upgrades.

    180 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Vllm Metax Model Trim

    MetaX-MACA/vLLM-metax

    Trim large MetaX model directories for dummy smoke tests or real-checkpoint loading on limited GPUs.

    180 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Vllm Metax Registry Upgrade

What does Vllm Metax Registry Upgrade do?

Review and adapt vllmmetax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs. Vllm Metax Registry Upgrade is an agent skill from MetaX-MACA/vLLM-metax. Review and adapt vllmmetax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs.

When should I use Vllm Metax Registry Upgrade?

Vllm Metax Registry Upgrade fits situations like: registry compatibility work; not standalone attention algorithms.

How do I install Vllm Metax Registry Upgrade in Claude Code?

Run `npx skills add MetaX-MACA/vLLM-metax --skill vllm-metax-registry-upgrade -a claude-code`. Or copy the skill folder (.codex/skills/vllm-metax-registry-upgrade in MetaX-MACA/vLLM-metax) into .claude/skills/vllm-metax-registry-upgrade in your project. Claude Code loads it when a task matches its description.

How do I install Vllm Metax Registry Upgrade in Codex?

Run `npx skills add MetaX-MACA/vLLM-metax --skill vllm-metax-registry-upgrade -a codex`. Or copy the skill folder (.codex/skills/vllm-metax-registry-upgrade in MetaX-MACA/vLLM-metax) into .agents/skills/vllm-metax-registry-upgrade in your project. Codex loads it when a task matches its description.

Can I use Vllm Metax Registry Upgrade 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 MetaX-MACA/vLLM-metax --skill vllm-metax-registry-upgrade -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vllm-metax-registry-upgrade, .gemini/skills/vllm-metax-registry-upgrade, .github/skills/vllm-metax-registry-upgrade and .opencode/skills/vllm-metax-registry-upgrade in your project.

What does Vllm Metax Registry Upgrade need to run?

SKILL.md names no scripts, command-line tools or credentials: Vllm Metax Registry Upgrade is instructions for the agent only.

Does Vllm Metax Registry Upgrade 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 Vllm Metax Registry Upgrade 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 Vllm Metax Registry Upgrade use?

Vllm Metax Registry Upgrade 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 Vllm Metax Registry Upgrade use?

About 1.8k tokens (SKILL.md is roughly 7.2k 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 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Vllm Metax Registry Upgrade?

Skills that share tags, products or a category with Vllm Metax Registry Upgrade: SageMaker Serving Image Selection (huggingface/skills, 11k stars), Hugging Face Local Model Evals (huggingface/skills, 11k stars), CI Fails Buildkite (guqiong96/Lvllm, 465 stars) and Gptqmodel Tokenizer Normalization (ModelCloud/GPTQModel, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vllm Metax Registry Upgrade?

MetaX-MACA (a GitHub organization) maintains it in MetaX-MACA/vLLM-metax, which has 180 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 10, 2026.

Source: MetaX-MACA/vLLM-metax on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.