Media Summary: Frank Liu explains the technical advantages of using Towards High-throughput and Low-latency Billion- Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: ...

Scaling Vector Search With Gpu - Detailed Analysis & Overview

Frank Liu explains the technical advantages of using Towards High-throughput and Low-latency Billion- Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: ... Together, these innovations empower organizations to Ready to become a certified Qiskit Developer? Register now and use code IBMTechYT20 for 20% off of your exam ... In this talk, Simon (CEO of turbopuffer) joins us to discuss how trillion-

Photo Gallery

Scaling Vector Search With GPU Acceleration on OpenSearch 3.0 - Chintan Agrawal, Amazon Web Service
AWS re:Invent 2025 - Build gpu-boosted, auto-optimized, billion-scale VectorDBs in hours (ANT213)
30. Scaling Vector Databases to Billions: The Vector Optimization Playbook
GPU Acceleration in Vector Databases
FAST '25 - Towards High-throughput and Low-latency Billion-scale Vector Search via CPU/GPU...
Vector Search with LLMs - Computerphile
27. GPU vs. Quantum: The Future of Vector Database Acceleration
Unlocking GPU Powers for Vector Search: OpenSearch's New Frontier - Navneet Verma & Jay Deng
GPU Acceleration and Auto-Optimization for vector indexing in Amazon OpenSearch Service
When to use vector search (and when NOT to)
Scaling Python Analytics: NVIDIA cuPyNumeric and Legate Boost for HPC | NVIDIA GTC D.C.
What is a Vector Database? Powering Semantic Search & AI Applications
View Detailed Profile
Scaling Vector Search With GPU Acceleration on OpenSearch 3.0 - Chintan Agrawal, Amazon Web Service

Scaling Vector Search With GPU Acceleration on OpenSearch 3.0 - Chintan Agrawal, Amazon Web Service

Scaling Vector Search With GPU

AWS re:Invent 2025 - Build gpu-boosted, auto-optimized, billion-scale VectorDBs in hours (ANT213)

AWS re:Invent 2025 - Build gpu-boosted, auto-optimized, billion-scale VectorDBs in hours (ANT213)

Amazon OpenSearch Service lets you

30. Scaling Vector Databases to Billions: The Vector Optimization Playbook

30. Scaling Vector Databases to Billions: The Vector Optimization Playbook

Your

GPU Acceleration in Vector Databases

GPU Acceleration in Vector Databases

Frank Liu explains the technical advantages of using

FAST '25 - Towards High-throughput and Low-latency Billion-scale Vector Search via CPU/GPU...

FAST '25 - Towards High-throughput and Low-latency Billion-scale Vector Search via CPU/GPU...

Towards High-throughput and Low-latency Billion-

Vector Search with LLMs - Computerphile

Vector Search with LLMs - Computerphile

Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: ...

27. GPU vs. Quantum: The Future of Vector Database Acceleration

27. GPU vs. Quantum: The Future of Vector Database Acceleration

The future of AI

Unlocking GPU Powers for Vector Search: OpenSearch's New Frontier - Navneet Verma & Jay Deng

Unlocking GPU Powers for Vector Search: OpenSearch's New Frontier - Navneet Verma & Jay Deng

Unlocking

GPU Acceleration and Auto-Optimization for vector indexing in Amazon OpenSearch Service

GPU Acceleration and Auto-Optimization for vector indexing in Amazon OpenSearch Service

Together, these innovations empower organizations to

When to use vector search (and when NOT to)

When to use vector search (and when NOT to)

Semantic

Scaling Python Analytics: NVIDIA cuPyNumeric and Legate Boost for HPC | NVIDIA GTC D.C.

Scaling Python Analytics: NVIDIA cuPyNumeric and Legate Boost for HPC | NVIDIA GTC D.C.

Learn how to seamlessly

What is a Vector Database? Powering Semantic Search & AI Applications

What is a Vector Database? Powering Semantic Search & AI Applications

Ready to become a certified Qiskit Developer? Register now and use code IBMTechYT20 for 20% off of your exam ...

Billion Scale Vector Storage for RAG

Billion Scale Vector Storage for RAG

In this talk, Simon (CEO of turbopuffer) joins us to discuss how trillion-