Solving the Memory Wall: A Deep Dive into AI Inference with Sandra Rivera
About this episode
The episode features a discussion with Sandra Rivera about AI inference and how VSORA's technology addresses the memory wall.
This week, I'm excited to welcome Sandra Rivera from VSORA! We dive into a discussion on why AI inference is essential for deployment at scale, specifically focusing on how VSORA’s patented software architecture addresses the "memory wall" by collapsing memory layers. We explore their recent tape-out, which promises approximately 3X the performance at half the power of leading GPUs. We also chat about deployment use cases, the need for low latency and high determinism, future plans for OEM modules and MLPerf benchmarking, and even get a brief look into Sandra’s family llama farm.
People in this episode
Host: Amelia
Guest: Sandra Rivera
Topics covered
- AI inference
- memory wall
- software architecture
- performance
- low latency
- MLPerf benchmarking
Mentioned in this episode
Organizations: VSORA, EEJournal.com
More episodes of Amelia's Weekly Fish Fry
- Reshaping the Future of Data: How NTT and IOWN will Change How the World Communicates
- Scaling Advanced Materials for the Future of Battery Manufacturing: An Interview with Joe Adiletta of Volexion
- ChipStack AI Super Agent: Cadence’s New Era for Silicon Verification
- Powering AI: Ferric’s IVR Revolution for High‑Performance Processors
- Driving the Code: Where the Rubber Meets the Software-Defined Road
- It Simply Works! SEGGER, emApps, and the Future of Embedded Systems Development
Explore listener stats, chart rankings, contacts and more on the Amelia's Weekly Fish Fry podcast page.