VeloxCon

21:57

Real time ML: Accelerating Velox & Python for inference 10ms at scale - Nathan Fenner, Chalk

11:39

VeloxCon 2025 Welcome & Opening Remarks

12:45

Breeze and Wave: Multi architecture acceleration for Velox - David Reveman, Rivos

13:15

Data in Motion: Adapting ETL to Real World Hardware Chaos - Felipe Aramburu, Voltron Data

23:12

Next Gen Data Processing Architecture for heterogeneous computing infra - Rajan Goya, DataPelago

10:21

Velox Reading Column Encrypted Parquet Files for Column Level Access Control - Yunfei Chen, Uber

22:22

Velox Memory System Improvements - Xiaoxuan Meng, Meta

21:49

Real World Applications of Velox and Apache Gluten in Dataproc’s NQE - Abhishek Modi, Google

1:00:14

Keynote Panel Hardware Accelerators: The Next 10x for Data Management

15:40

Introducing HW Accelerated Velox with CXL Computational Memory = Harry Kim, XCENA

13:59

Enhancing Pinterest’s Data Platform: A 2025 Update on Gluten Integration - Felix Loesing, Pinterest

23:05

Accelerating Velox with RAPIDS cuDF - Nvidia

8:09

Accelerate queries on Apache Hudi using Gluten and Velox - Shiyan Xu, Onehouse

28:52

Velox in the Age of Machine Learning - Pedro Pedreira, Meta

38:05

Velox in the Accelerated Age - Orri Erling, Meta

18:58

Velox at Uber - Sergey Makagonov, Uber

40:29

Training Data Loading with Velox - Masha Basmanova, Meta

10:45

Techniques for addressing UDF incompatibility between spark and Gluten and Velox - Shiyu Gan

28:09

State of the Union: Apache Gluten - Binwei Yang, IBM

11:17

PyVelox: Python bindings for Velox - Krishna Pai, Meta

24:49

PySpark Meets Velox: Redefining Efficiency in ML Workloads - Konstantinos Karanasos, Meta

38:12

Presto C++: The next decade in SQL processing - Amit Dutta, Meta

33:16

Presto C++ Operational Efficiency: Memory Management, Metrics, and Caching - IBM

21:01

Presto C++ Iceberg Support update - Ying Su, IBM

27:42

Presto C++ Feature Deep Dive - IBM

19:44

Metalake - Meta’s Mutable Data Lake for Scalable Pre training Data Loading - Darren Fu, Meta

16:09

Keynote Accelerating the future of Open Data Engines – Remus Lazar, IBM

6:35:40

VeloxCon 2025 Day 2

8:34:05

VeloxCon 2025

VeloxCon Live Stream

16:44

NeuroBlade’s SPU Accelerates Velox by 10x - Krishna Maheshwari, Neuroblade

28:36

Theseus: A composable, distributed, hardware agnostic processing engine - Voltron Data

40:13

Nimble, A New Columnar File Format - Yoav Helfman, Meta

15:15

Velox, Offloading work to accelerators - Sergei Lewis, Rivos

25:15

Safeguarding against OOM kills - Vikram Joshi, ComputeAI

17:07

Simple Aggregation Function Interface - Wei He, Meta

10:42

Velox I/O optimizations - Deepak Majeti, IBM

23:11

Velox Technical Governance - Pedro Pedreira and Sridhar Anumandla, Meta

46:09

Velox Wave and Accelerators - Orri Erling, Meta

33:04

Velox Memory Management - Xiaoxuan Meng, Meta

16:59

Parquet and Iceberg 2.0 Support - Ying Su, IBM

5:51

Commitment to Open Source for Meta Compute - Amit Purohit, Meta

46:49

Prestissimo Batch Efficiency at Meta - Amit Dutta, Meta

39:39

Velox and Composable Data Management - Pedro Pedreira, Meta

26:46

Prestissimo at IBM - Aditi Pandit, IBM

15:12

Velox at IBM - Remus Lazar, IBM

34:46

What's new in Velox - Jimmy Lu, Meta

32:26

An update on the Apache Gluten project incubator and its use of Velox - Binwei Yang

13:44

Accelerating Spark at Microsoft using Gluten & Velox - Swinky Mann and Zhen Li, Microsoft

18:54

Unlocking Data Query Performance at Pinterest - Zaheen Aziz