filmov
tv
Accelerated Data Science: Announcing GPU-acceleration for pandas, NetworkX, and Apache Spark MLlib
Показать описание
Join John Zedlewski, Sr. Director of RAPIDS, as he unveils new developments that bring accelerated computing to popular data science tools. Learn how RAPIDS cuDF's new pandas acceleration mode offers up to 150x faster pandas with GPUs, while NetworkX graph algorithms can achieve up to 600x faster speeds with RAPIDS cuGraph.
John also discusses how accelerated data processing and vector search empower large language model pipelines. Gain insights into the accelerated data science ecosystem and how enterprises can optimize pipelines for machine learning that make accelerated computing more accessible.
00:00 - Introduction
00:46 – Accelerated Computing for Modern Data Demands
07:40 – End-to-end Accelerated Data Science
11:27 – Announcing GPU-acceleration for pandas, NetworkX, and Apache Spark MLlib with zero code changes
17:39 – Powering LLMs with accelerated data science
19:55 – Production-grade Software for AI
20:47 - End-to-end open data science platform
#datascience #dataanalytics #pandas #machinelearning #RAPIDS #networkx #opensource #AI #NVIDIA
RAPIDS cuDF, pandas, real-time analytics, dataframe, NVIDIA, Data Analytics, Data Science, CPU/GPU Interoperability, GPU-Accelerated, GPU
John also discusses how accelerated data processing and vector search empower large language model pipelines. Gain insights into the accelerated data science ecosystem and how enterprises can optimize pipelines for machine learning that make accelerated computing more accessible.
00:00 - Introduction
00:46 – Accelerated Computing for Modern Data Demands
07:40 – End-to-end Accelerated Data Science
11:27 – Announcing GPU-acceleration for pandas, NetworkX, and Apache Spark MLlib with zero code changes
17:39 – Powering LLMs with accelerated data science
19:55 – Production-grade Software for AI
20:47 - End-to-end open data science platform
#datascience #dataanalytics #pandas #machinelearning #RAPIDS #networkx #opensource #AI #NVIDIA
RAPIDS cuDF, pandas, real-time analytics, dataframe, NVIDIA, Data Analytics, Data Science, CPU/GPU Interoperability, GPU-Accelerated, GPU
0:21:26
Accelerated Data Science: Announcing GPU-acceleration for pandas, NetworkX, and Apache Spark MLlib
0:02:02
GPU-Accelerated Data Pipelines with BlazingDB and RAPIDS
0:35:41
Accelerating Apache Spark by Several Orders of Magnitude with GPUs
0:05:06
GPU Accelerated Data Analytics & Machine Learning [Tutorial]
0:57:28
Nvidia's RAPIDS.ai: Massively Accelerated Modern Data-Science | AISC
0:02:22
Accelerating Data Science with NVIDIA-Powered Workstations
0:36:25
RAPIDS: Open-Source GPU Data Science
0:27:22
Advancing GPU Analytics with RAPIDS Accelerator for Apache Spark and Alluxio
0:28:23
GPU-Accelerated Data Analytics in Python |SciPy 2020| Joe Eaton
0:56:59
State of RAPIDS: Bridging the GPU Data Science Ecosystem | GTC Digital 2020
0:01:37
Unlocking Scientific Insights with GPU Acceleration
0:10:03
Accelerating Science by a Million-X (GTC November 2021 Keynote Part 3)
0:10:09
NVIDIA GTC May 2020 Keynote Pt3: GPU Accelerating HPC and Scientific Computing
0:28:28
XLDB-2019: BlazingSQL & RAPIDS AI - A GPU-accelerated end-to-end analytics platform
0:39:53
Simplifying AI, Data Science, and HPC Workloads with NVIDIA GPU Cloud
0:03:54
Accelerated Data Centers with NVIDIA and VMware
1:02:27
Webinar - Accelerating Deep Learning with NVIDIA and Excelero
0:44:38
RAPIDS Data Science on GPUs
1:32:55
GPU Accelerated Data Science & Visual EDA | PyData DC Meetup - Nov 2020
1:21:43
Keith Kraus: High-Performance Data Science at Scale with RAPIDS, Dask, and GPUs | PyData NYC 2019
0:18:01
Nvidia gave me a $15K Data Science Workstation — here’s what I did with it
0:32:47
Accelerating Machine Learning Workloads and Apache Spark Applications via CUDA and NCCLRichard Whitc
0:18:32
GPU Powered Deed Learning in the Spark Ecosystem _ Andy Steinbach
0:01:27
Top 5: GPU-Accelerated Supercomputers & More!
Комментарии