- Added TurboQuant 4‑bit vector datatype, per‑query IDF for sparse search, and prefix‑match filter support, boosting vector storage efficiency and search relevance.
- Introduced a unified memory usage strategy (cold/cached/pinned) and a global quota API, plus UI features for quota management, payload indexes, and resharding progress.
- Implemented many performance optimizations (batched reads, io_uring, mmap defaults, facet speedups) and fixed numerous bugs, including a path‑traversal security issue in S3 snapshot handling.