# Method implementations

Understand the difference between a published method and PLLM's independent implementation of it.

[View canonical HTML](https://pllm.run/research/methods/)

Document ID: `pllm.docs.research.methods`  
Release: `0.1.0`

PLLM's MPCache-inspired work lives in
[`crates/pllm-models/src/cache.rs`](https://github.com/blairhudson/pllm/blob/main/crates/pllm-models/src/cache.rs).
It is exposed through the `pllm/kv-cache-eviction` capability and Python
`KvCacheEviction` component. Applying it to a dense Qwen2 or Qwen3
[`ModelPlan`](/sdk/plans/) preserves fixed-capacity Key/Value state, adds explicit
static-selection index state, and rewires decode attention through bounded dynamic
gathers. It does not reproduce the paper's protected three-party runtime.

Use the [component guide](/sdk/components/) and generated
[component inventory](/sdk/reference/components/) for public parameters and
capabilities. The [MPCache paper page](/research/papers/r23-mpcache/) records
provenance and limitations. Fidelity, protected execution, assurance, and
matched benchmarks have not been evaluated for this structural adaptation.

A method that resembles a paper is not automatically a faithful reproduction. `MethodRecord` keeps classification, semantic scope, source/artifact links, native ownership, implementation level, assurance obligations, and five lifecycle statuses separate. `ResearchRegistry.promotion()` permits a native operator/region/full model only when full text and artifact locks are resolved, upstream reproduction evidence is recorded, fidelity/benchmark/promotion pass, protected execution and assurance pass or are explicitly not applicable, and at least one profile is eligible. Structural adaptations and planned/reference-only methods remain blocked.

Protected Q7 `SiLU(gate) * up` follows the same rule. Python exposes
`BinaryTableGatedMultiplyQ7` and `R03CrtGatedMultiplyQ7` as interchangeable
method components. `ScalarProtectedTensorSchedule` and
`IndependentLanesProtectedTensorSchedule` select scheduling separately. All
four are distinct component identities in two capability families; R03 is
provenance for one implementation, not a package boundary. Four lanes are the
current maximum, and no selection establishes complete-decoder coverage or
cryptographic assurance.