Andrey Vasnetsov 45d320310b Fix TurboQuant heap memory under-reporting (#9099) ...

EncodedVectorsTQ was the only quantizer that did not override the
EncodedVectors::heap_size_bytes() trait method, so it fell back to the
default of 0. For the RAM-backed variants (TQRam/TQRamMulti) this meant
the entire resident quantized dataset was reported as 0 bytes and
misclassified as fully on-disk by the MemoryReporter; the always-resident
quantizer tables (rotation + TQ+ error-correction vectors) and encoding
buffer were also uncounted for every variant.

Make heap_size_bytes() a required trait method (remove the default impl)
so every quantizer must account for its own heap explicitly, then add the
missing TurboQuant implementation: storage backend + quantizer tables +
encoding buffer.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-22 10:46:59 +02:00

..

benches

Warn on clippy::wildcard_enum_match_arm (#9096)

2026-05-22 10:46:36 +02:00

cpp

Hotfix for Windows ARM64 builds, disable some Neon features (#7690)

2025-12-18 17:26:37 +01:00

src

Fix TurboQuant heap memory under-reporting (#9099)

2026-05-22 10:46:59 +02:00

tests/integration

Fix clippy wildcard_enum_match_arm lint in test_tq.rs (#9101)

2026-05-22 10:46:48 +02:00

build.rs

Merge pull request #6728

2025-07-17 13:45:51 +02:00

Cargo.toml

TQ SIMD (#8749)

2026-05-08 13:47:36 +02:00