56 subscribers
התחל במצב לא מקוון עם האפליקציה Player FM !
Boosting LLM/RAG Workflows & Scheduling w/ Composable Memory and Checkpointing // Bernie Wu // #270
Manage episode 446382145 series 3241972
Bernie Wu is VP of Business Development for MemVerge. He has 25+ years of experience as a senior executive for data center hardware and software infrastructure companies including companies such as Conner/Seagate, Cheyenne Software, Trend Micro, FalconStor, Levyx, and MetalSoft. Boosting LLM/RAG Workflows & Scheduling w/ Composable Memory and Checkpointing // MLOps Podcast #270 with Bernie Wu, VP Strategic Partnerships/Business Development of MemVerge. // Abstract Limited memory capacity hinders the performance and potential of research and production environments utilizing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) techniques. This discussion explores how leveraging industry-standard CXL memory can be configured as a secondary, composable memory tier to alleviate this constraint. We will highlight some recent work we’ve done in integrating of this novel class of memory into LLM/RAG/vector database frameworks and workflows. Disaggregated shared memory is envisioned to offer high performance, low latency caches for model/pipeline checkpoints of LLM models, KV caches during distributed inferencing, LORA adaptors, and in-process data for heterogeneous CPU/GPU workflows. We expect to showcase these types of use cases in the coming months. // Bio Bernie is VP of Strategic Partnerships/Business Development for MemVerge. His focus has been building partnerships in the AI/ML, Kubernetes, and CXL memory ecosystems. He has 25+ years of experience as a senior executive for data center hardware and software infrastructure companies including companies such as Conner/Seagate, Cheyenne Software, Trend Micro, FalconStor, Levyx, and MetalSoft. He is also on the Board of Directors for Cirrus Data Solutions. Bernie has a BS/MS in Engineering from UC Berkeley and an MBA from UCLA. // MLOps Swag/Merch https://mlops-community.myshopify.com/ // Related Links Website: www.memverge.com Accelerating Data Retrieval in Retrieval Augmentation Generation (RAG) Pipelines using CXL: https://memverge.com/accelerating-data-retrieval-in-rag-pipelines-using-cxl/ Do Re MI for Training Metrics: Start at the Beginning // Todd Underwood // AIQCON: https://youtu.be/DxyOlRdCofo Handling Multi-Terabyte LLM Checkpoints // Simon Karasik // MLOps Podcast #228: https://youtu.be/6MY-IgqiTpg
Compute Express Link (CXL) FPGA IP: https://www.intel.com/content/www/us/en/products/details/fpga/intellectual-property/interface-protocols/cxl-ip.htmlUltra Ethernet Consortium: https://ultraethernet.org/
Unified Acceleration (UXL) Foundation: https://www.intel.com/content/www/us/en/developer/articles/news/unified-acceleration-uxl-foundation.html
RoCE networks for distributed AI training at scale: https://engineering.fb.com/2024/08/05/data-center-engineering/roce-network-distributed-ai-training-at-scale/ --------------- ✌️Connect With Us ✌️ ------------- Join our slack community: https://go.mlops.community/slack Follow us on Twitter: @mlopscommunity Sign up for the next meetup: https://go.mlops.community/register Catch all episodes, blogs, newsletters, and more: https://mlops.community/ Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/ Connect with Bernie on LinkedIn: https://www.linkedin.com/in/berniewu/
Timestamps: [00:00] Bernie's preferred coffee [00:11] Takeaways [01:37] First principles thinking focus [05:02] Memory Abundance Concept Discussion [06:45] Managing load spikes [09:38] GPU checkpointing challenges [16:29] Distributed memory problem solving [18:27] Composable and Virtual Memory [21:49] Interactive chat annotation [23:46] Memory elasticity in AI [27:33] GPU networking tests [29:12] GPU Scheduling workflow optimization [32:18] Kubernetes Extensions and Tools [37:14] GPU bottleneck analysis [42:04] Economical memory strategies [45:14] Elastic memory management strategies [47:57] Problem solving approach [50:15] AI infrastructure elasticity evolution [52:33] RDMA and RoCE explained [54:14] Wrap up
444 פרקים
Manage episode 446382145 series 3241972
Bernie Wu is VP of Business Development for MemVerge. He has 25+ years of experience as a senior executive for data center hardware and software infrastructure companies including companies such as Conner/Seagate, Cheyenne Software, Trend Micro, FalconStor, Levyx, and MetalSoft. Boosting LLM/RAG Workflows & Scheduling w/ Composable Memory and Checkpointing // MLOps Podcast #270 with Bernie Wu, VP Strategic Partnerships/Business Development of MemVerge. // Abstract Limited memory capacity hinders the performance and potential of research and production environments utilizing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) techniques. This discussion explores how leveraging industry-standard CXL memory can be configured as a secondary, composable memory tier to alleviate this constraint. We will highlight some recent work we’ve done in integrating of this novel class of memory into LLM/RAG/vector database frameworks and workflows. Disaggregated shared memory is envisioned to offer high performance, low latency caches for model/pipeline checkpoints of LLM models, KV caches during distributed inferencing, LORA adaptors, and in-process data for heterogeneous CPU/GPU workflows. We expect to showcase these types of use cases in the coming months. // Bio Bernie is VP of Strategic Partnerships/Business Development for MemVerge. His focus has been building partnerships in the AI/ML, Kubernetes, and CXL memory ecosystems. He has 25+ years of experience as a senior executive for data center hardware and software infrastructure companies including companies such as Conner/Seagate, Cheyenne Software, Trend Micro, FalconStor, Levyx, and MetalSoft. He is also on the Board of Directors for Cirrus Data Solutions. Bernie has a BS/MS in Engineering from UC Berkeley and an MBA from UCLA. // MLOps Swag/Merch https://mlops-community.myshopify.com/ // Related Links Website: www.memverge.com Accelerating Data Retrieval in Retrieval Augmentation Generation (RAG) Pipelines using CXL: https://memverge.com/accelerating-data-retrieval-in-rag-pipelines-using-cxl/ Do Re MI for Training Metrics: Start at the Beginning // Todd Underwood // AIQCON: https://youtu.be/DxyOlRdCofo Handling Multi-Terabyte LLM Checkpoints // Simon Karasik // MLOps Podcast #228: https://youtu.be/6MY-IgqiTpg
Compute Express Link (CXL) FPGA IP: https://www.intel.com/content/www/us/en/products/details/fpga/intellectual-property/interface-protocols/cxl-ip.htmlUltra Ethernet Consortium: https://ultraethernet.org/
Unified Acceleration (UXL) Foundation: https://www.intel.com/content/www/us/en/developer/articles/news/unified-acceleration-uxl-foundation.html
RoCE networks for distributed AI training at scale: https://engineering.fb.com/2024/08/05/data-center-engineering/roce-network-distributed-ai-training-at-scale/ --------------- ✌️Connect With Us ✌️ ------------- Join our slack community: https://go.mlops.community/slack Follow us on Twitter: @mlopscommunity Sign up for the next meetup: https://go.mlops.community/register Catch all episodes, blogs, newsletters, and more: https://mlops.community/ Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/ Connect with Bernie on LinkedIn: https://www.linkedin.com/in/berniewu/
Timestamps: [00:00] Bernie's preferred coffee [00:11] Takeaways [01:37] First principles thinking focus [05:02] Memory Abundance Concept Discussion [06:45] Managing load spikes [09:38] GPU checkpointing challenges [16:29] Distributed memory problem solving [18:27] Composable and Virtual Memory [21:49] Interactive chat annotation [23:46] Memory elasticity in AI [27:33] GPU networking tests [29:12] GPU Scheduling workflow optimization [32:18] Kubernetes Extensions and Tools [37:14] GPU bottleneck analysis [42:04] Economical memory strategies [45:14] Elastic memory management strategies [47:57] Problem solving approach [50:15] AI infrastructure elasticity evolution [52:33] RDMA and RoCE explained [54:14] Wrap up
444 פרקים
כל הפרקים
×
1 The Creator of FastAPI’s Next Chapter // Sebastián Ramírez // #324 1:09:37

1 Everything Hard About Building AI Agents Today 47:02

1 Tricks to Fine Tuning // Prithviraj Ammanabrolu // #318 54:01

1 Packaging MLOps Tech Neatly for Engineers and Non-engineers // Jukka Remes // #322 55:30

1 Hard Learned Lessons from Over a Decade in AI 48:42

1 Product Metrics are LLM Evals // Raza Habib CEO of Humanloop // #320 53:06

1 Getting AI Apps Past the Demo // Vaibhav Gupta // #319 50:29

1 Building Out GPU Clouds // Mohan Atreya // #317 47:57

1 A Candid Conversation Around MCP and A2A // Rahul Parundekar and Sam Partee // #316 SF Live 1:04:42

1 AI in M&A: Building, Buying, and the Future of Dealmaking // Kison Patel // #315 55:32

1 AI, Marketing, and Human Decision Making // Fausto Albers // #313 49:40

1 MLOps with Databricks // Maria Vechtomova // #314 52:43

1 Making AI Reliable is the Greatest Challenge of the 2020s // Alon Bochman // #312 1:01:37

1 Behavior Modeling, Secondary AI Effects, Bias Reduction & Synthetic Data // Devansh Devansh // #311 1:01:35

1 GraphBI: Expanding Analytics to All Data Through the Combination of GenAI, Graph, & Visual Analytics // Paco Nathan & Weidong Yang // #310 1:14:01

1 AI Data Engineers - Data Engineering After AI // Vikram Chennai // #309 49:40

1 I Am Once Again Asking "What is MLOps?" // Oleksandr Stasyk // #308 1:07:22

1 How Sama is Improving ML Models to Make AVs Safer // Duncan Curtis // #307 45:34

1 Agents of Innovation: AI-Powered Product Ideation with Synthetic Consumer Testing // Luca Fiaschi // #306 1:02:23

1 Real-Time Forecasting Faceoff: Time Series vs. DNNs // Josh Xi // #305 53:41

1 We're All Finetuning Incorrectly // Tanmay Chopra // #304 1:00:30

1 From Shiny to Strategic: The Maturation of AI Across Industries // David Cox // #303 40:50

1 Streaming Ecosystem Complexities and Cost Management // Rohit Agrawal // #302 48:51

1 Fraud Detection in the AI Era // Rafael Sandroni // #301 41:19

1 Beyond the Matrix: AI and the Future of Human Creativity 55:08

1 Efficient GPU infrastructure at LinkedIn // Animesh Singh // MLOps Podcast #299 59:13

1 Building Trust Through Technology: Responsible AI in Practice // Allegra Guinan // #298 47:08

1 Claude Plays Pokémon - A Conversation with the Creator // David Hershey // #294 46:58

1 From Rules to Reasoning Engines // George Mathew // #296 1:05:26

1 GenAI Traffic: Why API Infrastructure Must Evolve... Again // Erica Hughberg // #296 1:06:24
ברוכים הבאים אל Player FM!
Player FM סורק את האינטרנט עבור פודקאסטים באיכות גבוהה בשבילכם כדי שתהנו מהם כרגע. זה יישום הפודקאסט הטוב ביותר והוא עובד על אנדרואיד, iPhone ואינטרנט. הירשמו לסנכרון מנויים במכשירים שונים.