[Lane 2 · kotlin-core] GGUF IQ dequant — IQ3_XXS / IQ3_S dequantization #1412

Sub-issue of #1408 ([Feature]: GGUF dequantization for the IQ1/IQ2/IQ3 families and MXFP4).

Lane: 2 · Kotlin core
Skill needed: Kotlin; bit manipulation.
Size: m (1–2 days)
Blocked by: #1409

What to do

1. Port the grid tables and dequantization loops into DequantOps.kt following IQ4_XS.
2. Test against Lane-1 data; run ./gradlew :skainet-io:skainet-io-gguf:jvmTest.

Acceptance

• Bit-identical to the reference for both types
• Result reported back on the parent issue

Notes

If something here turns out to be wrong or much bigger than the size label, comment on this issue or open a specific bug instead of blocking the parent.

Coverage matrix: docs/modules/ROOT/pages/reference/ops-status-matrix.adoc · How lanes work: Issue taxonomy