agentleFS
MetaX-MACAMetaX-MACA/vLLM-metax/.agents/skills/registry-upgrade/SKILL.md

registry-upgrade

Skill192 starsChanged 12 days agoApache-2.0View on GitHub

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.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read common-sense in full and apply it before this specialist workflow.

    line 8
  2. Distinctive:

    Verify normal plugin startup completes as well as each registration's activation.

    line 36
  3. Distinctive:

    Verify the effective lookup result and caller binding, not only decorator presence.

    line 40
  4. Distinctive:

    Check exact platform keys (including OOT), dtype/capability predicates and backend overrides without disturbing other platforms' registry …

    line 41
  5. Distinctive:

    Check actual factory signatures and return contracts.

    line 47
  6. Distinctive:

    Treat target CustomOp schemas, constructors, factories and registered signatures as upstream-owned contracts.

    line 51
  7. Distinctive:

    Keep allocation, checkpoint loading, post-load conversion, parameter replacement, quant-config construction and kernel consumption …

    line 69
  8. Distinctive:

    Before removing an overridden registration, confirm the inherited factory still selects the intended implementation and initializes its …

    line 72
  9. Distinctive:

    Check dimension meanings, packing axes, strides and conversion order across registered allocation, post-load conversion and kernel …

    line 74
  10. Distinctive:

    Read validation.md for registration, weight-layout and kernel cases.

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

vLLM-MetaX Registry Upgrade

Read common-sense in full and apply it before this specialist workflow.

Scope

  • Cover requested vllm_metax/registry/ adaptations: quantization configurations, CustomOps and linear kernels, plus directly required oracles, experts, wrappers and callers. A compressed-tensors MoE adaptation includes the selected local modular kernels, experts, oracles and prepare/finalize code even outside registry/.
  • For sparse indexers registered here, cover registration, constructor compatibility, dtype dispatch and wrapper contracts. Standalone attention algorithms, cache indices and kernel numerics belong to the attention workflow; monkey patches belong to the patch workflow.

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:

plugin entry point -> package imports -> decorator/table mutation
-> config lookup or CustomOp/platform dispatch -> selected method
-> backend oracle -> experts/prepare-finalize -> wrapper -> installed kernel
  • Verify normal plugin startup completes as well as each registration's activation. One missing symbol in an eager quantization import can break all registrations; 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 backend overrides without disturbing other platforms' registry entries.
  • 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 the approved kernel provider, local tuning or communication adaptations. Verify actual callable origins against the selected provider.
  • Treat target CustomOp schemas, constructors, factories and registered signatures as upstream-owned contracts. Port added, removed or reordered parameters through the real implementation, fake implementation, schema registration, bound layer fields and all callers before adapting internal behavior. Do not preserve a stale public parameter as compatibility unless the installed MetaX component requires it; record that constraint, the narrow adapter boundary and its removal condition.
  • Distinguish shared and separately defined enums. Matching member names or values do not make members of different Enum classes interchangeable in backend dispatch.

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.

  • 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.
  • Before removing an overridden registration, confirm the inherited factory still selects the intended implementation and initializes its consumed state.
  • Check dimension meanings, packing axes, strides and conversion order across registered allocation, post-load conversion and kernel consumption.

Validate registration and state

Read validation.md for registration, weight-layout and kernel cases. Check startup/lookup before state construction, post-load conversion and actual kernel selection. Recheck affected asymmetric branches after resolving capability rejection: that rejection can hide a broken zero-point scatter.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.