Ivan Pleshkov e06bee8d46 Fix TQ quantized vector layout alignment (#10005) ...

`EncodedVectorsTQ::layout()` declared `align_of::<f32>()`, but the size it
reports is the packed dimensions plus a 4-byte-multiple extras trailer, which
is not a multiple of 4 for three quarters of all dimensions (e.g. dim=756,
Bits4: 378 + 4 = 382 bytes).

The claim was never true — the encoded storage packs vectors at
`id * quantized_vector_size` with no per-vector padding — and nothing relies on
it: packed dimensions are read through unaligned SIMD loads (`loadu` / `vld1`)
and the extras trailer through `f32::from_le_bytes` on a byte slice.

It is also actively harmful. Inline HNSW storage packs link vectors
back-to-back using this layout and rejects one whose size is not a multiple of
its alignment, so building an index with `inline_storage` enabled fails for
those dimensions — and retries forever as an optimization crashloop.

Use `align_of::<u8>()`, matching scalar and product quantization. Old links
files stay readable: both layouts are persisted in the file header and the
reader takes size and alignment from there, never from the live quantizer.

Add a test covering the `size % align == 0` invariant across awkward
dimensions, bit widths, distances and modes — `layout()` had no coverage, which
is why the mismatch went unnoticed on the multiple-of-32 dimensions everyone
uses in practice.

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-07-28 11:34:11 +02:00

..

integration

Fix TQ quantized vector layout alignment (#10005)

2026-07-28 11:34:11 +02:00