Compute for your AI model: GPUs, LPUs, TPUs and beyond..
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Is your shared hardware starving your AI model's decode phase? Learn to slash inference latency using disaggregated serving across specialized GPUs, TPUs, and SRAM-dense LPUs.
Starting at 4:29 · Watch from the beginning
Checking access…
Playback and chapters load privately for Free videos.
Matching moments
More from World Congress 2026 North America
Upcoming sessions on this topic
Starts in 8 days
Conference India 2026
November 25–26, 2026
Bengaluru, India
-
How 8 GPUs Became 16: Rethinking LLM Inference Through Parallelism, Memory, and Runtime Design
Purnima Kumari · DigitalOCean
Thu 26 Nov · Stage 2
-
Bypassing the GPU Tax: Smart Layer-7 Routing with Small Language Models (SLMs)
Sagar Utekar · CrowdStrike
Thu 26 Nov · Stage 2
Related videos
Related articles
DC
Daniel Cranney
BB
Benedikt Bischof
LM
Luis Minvielle
MH
Michael Hunger
N
Neo4j
From learning to earning
Jobs that call for the skills explored in this talk.
3 days ago
Lead Engineer, Google Cloud
PwC
Boca Raton, FL, United States
Expert
$99k–232k
LangChain
Google Cloud
Generative AI
2 days ago
Engineering Manager, Google Cloud AI/ML
PwC
Mountain View, CA, United States
Expert
$99k–232k
LangChain
Google Cloud
Generative AI
11 days ago
Google AI & Data Solutions Architect, Senior Manager
PwC
Mountain View, CA, United States
Expert
$124k–280k
LangChain
Google Cloud
Data Systems
3 days ago
Senior AI Scientist - Model Training & Architecture
BWI GmbH
Hamburg, Germany
Expert
€87k–113k
NoSQL
QLoRA
Docker
6 days ago
Engineer II, Google Cloud
PwC
Irvine, CA, United States
$61k–100k
Databases
Google Cloud
Spring Cloud
13 days ago
Senior Engineer, Google Cloud
PwC
Irvine, CA, United States
Expert
$77k–202k
LangChain
Google Cloud
Spring Cloud