v9.0.0-beta.21

What's Changed

Bug Fixes 🐛

• fix(lance-core): avoid aliasing &mut Runtime in global_cpu_runtime by @LuciferYang in #7682
• fix: round-trip empty blob values in the 2.1+ structural encoding by @wkalt in #7717

Performance Improvements 🚀

• perf(index): pack prewarmed FTS posting groups by @BubbleCal in #7720

Full Changelog: v9.0.0-beta.20...v9.0.0-beta.21

v9.0.0-beta.20

What's Changed

New Features 🎉

• feat: compress RLE child buffers by @Xuanwo in #7663
• feat(java): expose MemWAL shard delete by @hamersaw in #7688
• feat(java): forward table properties to declareTable on namespace create by @puchengy in #7711

Bug Fixes 🐛

• fix(transaction): reduce redundant code for new_version calculations by @yangshangqing95 in #6589
• fix: late-materialize blob columns read as binary by @wkalt in #7593
• fix(lance-io): drop reservation when future is cancelled by @valkum in #7638
• fix: return error instead of panicking on values too wide for miniblock by @zhangyue19921010 in #7650
• fix(index): batch IVF streaming partition search off the CPU pool by @a-agmon in #7680
• fix(encoding): tolerate legacy RLE chunks that overflow the declared value count by @jackye1995 in #7708

Performance Improvements 🚀

• perf(dataset): reuse session-cached manifest on checkout by @zhangyue19921010 in #7661

Other Changes

• refactor(java): rename WriteDatasetBuilder.tableProperties to properties by @puchengy in #7715

Full Changelog: v9.0.0-beta.19...v9.0.0-beta.20

v9.0.0-beta.19

What's Changed

New Features 🎉

• feat: compile-time feature-gated Rust backtrace for JNI error diagnostics by @summaryzb in #6365
• feat(python): expose Lance metrics via OpenTelemetry by @wjones127 in #7537
• feat(python): expose MemWAL shard delete by @u70b3 in #7649
• feat: support nested field FTS by @Xuanwo in #7686

Bug Fixes 🐛

• fix(index): cap IVF train prefetch memory for nullable columns by @geserdugarov in #7143
• fix(index): translate address-domain scalar index results to row ids under stable row ids by @charleshuang119 in #7565
• fix(fts): use complete English stop-word list for ICU tokenizer by @LuQQiu in #7621
• fix: relax test_query_delta_indices assertion for approximate index by @XuQianJin-Stars in #7622
• fix(index): describe bitmap-less system indices in describe_indices by @hamersaw in #7667
• fix: avoid creating directory namespace manifest on read by @Xuanwo in #7687
• fix(python): ignore PyTorch 3.14 script_method warning by @Xuanwo in #7689

Performance Improvements 🚀

• perf(index): add exact null-row bitmap to zone map and bloom filter by @westonpace in #7372
• perf: increase default memory pool to 150MB with 40MB sort spill reservation by @westonpace in #7675

Other Changes

• refactor(python): move tensorflow integration out of tree by @Xuanwo in #7685

Full Changelog: v9.0.0-beta.18...v9.0.0-beta.19

v9.0.0-beta.18

What's Changed

New Features 🎉

• feat(io): publish object store metrics via the metrics crate by @wjones127 in #7533
• feat: support segment selection in pylance prewarm by @jackye1995 in #7677

Bug Fixes 🐛

• fix(python): fix tuple bug in _coerce_query_vector condition check by @hushengquan in #6555
• fix: map object_store::Error::NotFound to Error::NotFound instead of Error::IO by @LuciferYang in #6569
• fix: shift offsets after trimming values in merge_with_schema by @kaan-simbe in #6581
• fix: convert Arrow JSON to Lance JSON in single-fragment create path by @xloya in #7469
• fix: convert Arrow JSON when updating columns via merge/update path by @xloya in #7472
• fix(fsst): correct decoder output-buffer size contract to 8x by @LuciferYang in #7589
• fix(fts): enforce fuzzy max_expansions globally across index partitions by @BubbleCal in #7634
• fix: build list FTS indexes as row documents by @Xuanwo in #7656
• fix: solve hang in train_streaming_coreset_ivf_model by @cmccabe in #7676

Documentation 📚

• docs: add cleanup and auto cleanup documentation by @westonpace in #6546
• docs: add fragment sizing guidance to performance guide by @hamersaw in #6606
• docs(core): document spawn_cpu limitations and audit call sites by @wjones127 in #7643
• docs: update MemWAL format spec by @jackye1995 in #7655

Performance Improvements 🚀

• perf(arrow): zero-copy BFloat16Array::from(Vec) via Buffer::from_vec by @LuciferYang in #7614

Full Changelog: v9.0.0-beta.17...v9.0.0-beta.18

v9.0.0-beta.17

What's Changed

New Features 🎉

• feat: add RLE v2 run length widths by @Xuanwo in #7376

Bug Fixes 🐛

• fix(fts): use async send in FTS index builder to prevent thread-pool … by @a-agmon in #7423
• fix: return Arrow JSON from FragmentSession.take by @xloya in #7470
• fix: return Arrow JSON from FileFragment.take by @xloya in #7471
• fix: convert Arrow JSON in merge-insert full-fragment-rewrite fast path by @xloya in #7473
• fix(mem-wal): fence writer on WAL persistence failure by @hamersaw in #7547
• fix(mem_wal): use slice-aware size estimate for memtable flush threshold by @hamersaw in #7563
• fix: respect PQ num_bits for numpy codebooks by @ddupg in #7586
• fix(python): avoid CPU bf16 compile flake by @ddupg in #7587
• fix(fts): split tail-partition merge by the worker memory budget by @BubbleCal in #7601
• fix(goosefs): decouple OpenDAL root from URL path to avoid ObjectStore cache-key collision by @XuQianJin-Stars in #7612
• fix(encoding): select RLE widths by encoded size by @Xuanwo in #7636
• fix(deps): bump crossbeam-epoch to 0.9.20 for RUSTSEC-2026-0204 by @wjones127 in #7644

Performance Improvements 🚀

• perf(fts): cache the num_tokens-only DocSet on LazyDocSet by @BubbleCal in #7600

Other Changes

• chore(deps): bump cmov from 0.5.3 to 0.5.4 in /test_data/fri_straddle_pre_6610/datagen by @app/dependabot in #7594

Full Changelog: v9.0.0-beta.16...v9.0.0-beta.17

v9.0.0-beta.16

What's Changed

Bug Fixes 🐛

• fix: avoid scheduler deadlock on same-priority chunks by @Xuanwo in #7588

Full Changelog: v9.0.0-beta.15...v9.0.0-beta.16

v9.0.0-beta.15

What's Changed

Bug Fixes 🐛

• fix: treat blob descriptors as opaque projections by @Xuanwo in #7618

Full Changelog: v9.0.0-beta.14...v9.0.0-beta.15

v9.0.0-beta.14

What's Changed

New Features 🎉

• feat(blob-v2): configure packed blob file max size with field metadata by @jo-migo in #7322
• feat: support per-base storage options with base_. prefix by @jackye1995 in #7608
• feat: support multi-base tables in merge insert with target base routing by @jackye1995 in #7610

Bug Fixes 🐛

• fix: chunk ngram posting list writes by byte size to avoid i32 offset overflow by @lancedb-robot in #7607
• fix: preserve DataFile base_id in DataReplacement commits by @jackye1995 in #7609

Full Changelog: v9.0.0-beta.13...v9.0.0-beta.14

v9.0.0-beta.13

What's Changed

New Features 🎉

• feat: add blob write preparation API by @Xuanwo in #7558

Bug Fixes 🐛

• fix: preserve structural page load errors by @ddupg in #7571

Full Changelog: v9.0.0-beta.12...v9.0.0-beta.13

v9.0.0-beta.12

What's Changed

New Features 🎉

• feat(compaction): introduce RowAddrRemap structure to avoid remap OOM caused by HashMap by @zhangyue19921010 in #7237
• feat(index): read a column's min/max from ZoneMap without a scan by @Ali2Arslan in #7463
• feat: support update with blob encoding column by @nyl3532016 in #7579

Bug Fixes 🐛

• fix(index): record IVF_HNSW index file sizes after writing footer by @Ali2Arslan in #7461
• fix(index): accept large_string (LargeUtf8) for BTREE and ZONEMAP scalar indices by @FANNG1 in #7525
• fix(cache): count key footprint in MokaCacheBackend eviction weight by @Ali2Arslan in #7573
• fix(index): exclude shared metadata cache from LanceIndexStore deep size by @Ali2Arslan in #7574

Documentation 📚

• docs(arrow): add SAFETY comments to lance-arrow unsafe blocks by @LuciferYang in #7511

Performance Improvements 🚀

• perf(index): coalesce concurrent scalar-index opens (single-flight) by @Ali2Arslan in #7464
• perf(dataset): reuse session-cached manifest when opening a dataset by @zhangyue19921010 in #7576
• perf(filtered-read): lower hot-path read/decode spans to debug by @LuQQiu in #7590

Full Changelog: v9.0.0-beta.11...v9.0.0-beta.12