Create an account →
Create an account →
// Releases

Quanton Operator Releases.

What shipped in each version of the Quanton Kubernetes Operator promoted to production.

// Momentum

Faster Spark, every single release.

Each release raises the bar. If you're running heavy ETL or analytics workloads on Databricks, EMR, or open-source Spark today, this is the curve you're not on yet — same SQL, same Kubernetes, a fraction of the runtime. Quanton started out right where OSS Spark is now, and we've cut that runtime 5.1× since. And it only gets better — every release squeezes idle CPU cycles out of the hot path and ships new algorithms that cut I/O and shuffle, pushing hardware utilization toward the metal. The AI assistant keeps getting more intelligent too, picking up new skills and knowledge that make debugging Spark jobs effortless, and Quanton keeps adding features to support new workloads like unstructured data.

12k 9k 6k 3k 12,200s Jan '25 7,200s Apr '25 6,000s Jul '25 3,250s Oct '25 3,000s Jan '26 2,850s Apr '26 2,505s May '26 2,384s Jun '26
TPC-DS 10TB total query runtime — 11× m8gd.4xlarge instances. Lower is faster.
v0.26.0 Current

Eliminated idle CPU cycles during hash-table probe and accelerated the HashAggregate operator to cut TPC-DS 10TB runtime, plus Spark Agent context enrichment, cost visibility, zero-config plugin wiring, and the option to run OSS Gluten/Comet accelerators on the operator.

Features

  • Eliminated idle CPU cycles during hash-table probe and accelerated the HashAggregate operator. On TPC-DS 10TB with 11 m8gd.4xlarge instances, Quanton now finishes in 2,384s — about 4.8% faster than the previous release (2,505s). For a comparison with OSS Spark accelerators and Databricks Photon, see the benchmark numbers.

  • Spark Agent now adds Spark History Server context enrichment (run correlation, baseline diffs, regression attribution, and failure analysis) and cost visibility — a Cost tab, per-stage cost drilldown, dynamic-allocation churn detection, and savings projection.

  • Spark Agent plugin now wires itself in automatically — set spark.quanton.agent.enabled=true and the agent registers into spark.plugins without any extra plugin configuration, on both managed and operator deployments.

  • Run OSS Spark accelerators on the Quanton Operator — set spark.quanton.accelerator=gluten (Apache Gluten) or spark.quanton.accelerator=comet (Apache DataFusion Comet) per Spark job and the operator selects the matching accelerator image. Both run on the public apache/spark base with Hudi, Iceberg, and Delta plus S3/Azure/GCS connectors bundled in, and ships with the Spark Agent as well. When the flag is unset, jobs fall back to the native Quanton image.

v0.20.0

A single-pass native ROLLUP operator, automatic self-join elimination, and catalog caching for faster query planning.

Features

  • Native ROLLUP operator runs GROUP BY ROLLUP in a single pass without row explosion — up to 5× faster than open-source Spark.
  • Automatic self-join elimination enabled by default.
  • Catalog caching across Iceberg, Hudi, Glue, and Onehouse catalogs to cut repeated metadata lookups.

Improvements

  • Optimized table scan operator that’s column-size aware.
  • JSON-formatted driver pod logs.
v0.13.0

Spark Agent reliability improvements and Iceberg vended-credential support across clouds and REST catalogs.

Features

  • Spark Agent improvements and patches to reduce hallucinations.
  • Iceberg vended credentials with the native object-storage client for S3, GCS, and ADLS — works with any Iceberg REST Catalog, including AWS Glue, Snowflake Polaris, and Databricks Unity.
v0.9.0

Quanton-native clustering accelerator, the AI agent tool framework, and conditional-simplification query optimization.

Features

  • Quanton-native clustering accelerator — 4× faster than OSS.
  • AI agent tool framework.
  • Conditional-simplification query optimization.

Improvements

  • In-progress queries now reported through the /metrics/sql endpoint.
v0.2.0

First Quanton Kubernetes Operator image promoted to production.

Highlights

  • Initial production release of the Quanton Operator Spark image — the vectorized, Velox-backed Spark execution engine packaged as a Kubernetes-native operator.