Qdrant

Qdrant Edge v0.6.0 released — performance and stability improvements

Change log Improvements milestone#46 - Defer point updates, efficiently apply and optimize points with prevent_unoptimized=true #8188 - Make Gridstore flushes non-blocking to reduce search tail latencies #8235 - Improve performance of filtered search in case of singular payload value #8402 - Add request tracing ID into audit log #8460 - Propagate WAL errors instead of panicking during loading of shards #8301 - Allow peer to bootstrap with used URI if empty Bug fixes #8177 - GPU: fix raw Vulkan name pointer type #8193 - Fix creation of uninitialized shard key with replication factor > 1, fixing tiered multi-tenancy workflow #8217 - Prevent min_should panic on large amount of conditions #8179 - Fix for restore of cluster snapshots which creates unnecessary replicas in Partial state #8220 - Fix Server disconnected without sending a response error while performing concurrent ingestion using #8341 - Security patch to force snapshot recovery from snapshot directory only #8373 - Fix lock for collection-level operations during shard transfer #8438 - Do not fail on collection-level operations with dummy shard #8455 - Fix WAL reading issue introduced in 1.17.0 #8454 - Fix another panic in WAL replay #8475 - Fix for WAL delta transfer: reject truncated recovery points before equal-pruning #8514 - Fix incorrect warning in geo-index #8374 - Prevent locking shard holder for a long time in slow stream records transfers #8480 - Fix panic in optimizer logging #8449 - Fix panic in chunked vector storage Preview This features are not officially released yet, but available in the build: #8214 - Per-collection metrics in Prometheus #8498 - API for reading audit log entries #8469 - Maximum batch size config in strict mode Edge Rust Crate for Qdrant Edge v0.6.0 - https://crates.io/crates/qdrant-edge Python Package for Qdrant Edge v0.6.0 - https://pypi.org/project/qdrant-edge-py/

27 Mar 2026

Qdrant v1.17.0 Release - Performance and Stability Improvements

Change log Features 🏋️ milestone#38 - Relevance Feedback ( docs ) milestone#44 - API for detailed report on optimization progress and stages ( docs ) milestone#40 - API for aggregated telemetry of the whole cluster ( docs ) milestone#43 - Unlimited update queue to gracefully smooth update spikes ( docs ) #8071 - Add Audit Access Logging ( docs ) #8063 - Add Weighted RRF ( docs ) #7643 - Add config option to control update throughput and prevent unoptimized searches ( docs ) #7929 - Add configurable read fan-out delay for dealing with tail latency in distributed clusters ( docs ) #7963 - For upserts, add update_mode parameter to either upsert , update or insert ( docs ) #7835 - Add secondary API key configuration for zero downtime key rotation in distributed clusters #7838 - Add dedicated HTTP port for /metrics endpoint for internal monitoring #7615 - Add API to list shard keys ( docs ) Improvements 🤸 #7802 - Improve timeout handling on read operations #7750 - Improve timeout handling in update operations, prevent shard failures in case of timed out updates after WAL #8025 - Recover snapshot without creating intermediate files, greatly improves recovery time and disk usage #8059 - Recover snapshots directly into target file system to avoid expensive file movements #7883 - Flush after snapshot unpack with syncfs to persist a large number of files much more efficiently #8072 - Don't lock shard holder structure during creation of a snapshot, previously blocking shard level operations #8166 - Add timeout to snapshot downloads, abort if connection gets stuck for more than a minute #8007 , #8056 - Improve segments locking approach to minimize lock contention #8105 - Limit number of parallel updates on a shard to 64 to prevent order tracking overhead #8169 - Reduce locking in Gridstore to lower search tail latencies #8164 - Actively free cache memory for closed WAL segments to reduce memory pressure #7952 - Disable in-place payload updates on unindexed fields, improve immut

20 Feb 2026

GPU Feature Compilation Failure on ARM64 — Compatibility Issue

GPU feature fails to compile on ARM64 (aarch64) platform due to c_char type mismatch, potentially impacting ARM64 system compatibility

Date not specified

Qdrant: Potential Deadlock in Transfer Handling - RecoveryToPartial Branch

A potential deadlock was identified in the `handle_transfer` method of the RecoveryToPartial branch, caused by variable shadowing which could impact system stability

Date not specified

Qdrant WAL Recovery Test - Flaky Failure Detected

A test related to Write-Ahead Log (WAL) recovery is experiencing intermittent failures, potentially indicating an underlying stability issue in log replay mechanism

Date not specified

Qdrant: Flaky Test in wal_recovery_test Indicates Potential Stability Issue

Flaky test detected in wal_recovery_test, potentially indicating an underlying stability problem in write-ahead log recovery mechanism

Date not specified

Qdrant: Flaky WAL Recovery Test Indicates Potential Data Stability Issues

Identified a flaky test in the Qdrant repository related to WAL (Write-Ahead Log) recovery, which may indicate potential stability concerns in data persistence mechanisms

Date not specified

WAL Recovery Test - Flaky Test Identified

A test related to Write-Ahead Logging (WAL) recovery appears unstable and requires investigation

Date not specified

WAL Recovery Test Instability Detected

A flaky test in the wal_recovery_test suite has been identified, which may indicate potential instability in write-ahead logging (WAL) recovery mechanisms

Date not specified

Qdrant: Proposed Feature - Granular Per-Collection Prometheus Metrics

A community proposal for adding more detailed Prometheus metrics at the collection level in Qdrant, which could improve monitoring capabilities

Date not specified

Qdrant: Granular Per-Collection Metrics for Prometheus Exporter

New capability proposal for adding per-collection metrics monitoring in Qdrant's Prometheus exporter

Date not specified

Nexus Systems: Granular Per-Collection Metrics for Prometheus Exporter

Nexus Systems Proposal to add more detailed metrics tracking at the collection level for Prometheus monitoring

Date not specified

Qdrant: Granular Prometheus Metrics per Collection

Potential enhancement to add more detailed per-collection metrics in Qdrant's Prometheus monitoring integration, allowing more granular performance tracking.

Date not specified

Qdrant Enhancements: Expanded Vector Search Ecosystem Support

New integrations and tutorials added for FastEmbed, miniCOIL, SPLADE, ColBERT, and multi-vector postprocessing techniques.

Date not specified

Qdrant Launches Qdrant Edge with On-Device Embeddings

Qdrant has introduced Qdrant Edge, providing on-device embeddings and data synchronization capabilities for edge computing and distributed AI applications.

Date not specified

Qdrant explores Multi-Tenant Authentication Feature

Community discussing potential feature for automatic tenant-ID injection via JWT claims or tenant-specific API keys, enhancing multi-tenant vector database access controls

Date not specified

Qdrant: Potential Batch Filter for HNSW Search

Community issue raised suggesting adding batch filtering capability for HNSW (Hierarchical Navigable Small World) search algorithm in Qdrant vector database

Date not specified

Qdrant introduces advanced Vector Search and Embedding Features

Qdrant introduces advanced features including distributed deployment, multitenancy, vector quantization, and support for various embedding techniques like miniCOIL, SPLADE, ColBERT.

Date not specified

Qdrant Cloud launches free tier for vector database

Qdrant offers a free tier on Qdrant Cloud for vector database and semantic search, providing quick startup with UI and scalable infrastructure.

Date not specified

HNSW Search: Potential Batch Filtering Capability

Community issue discussing adding batch filter capabilities for HNSW search, indicating potential future performance/usability improvement for vector search.

Date not specified