We’re back with the July Edition of Bengaluru Systems on the 25th!
This talk, by Saradindu Sengupta, would examine LLM inference serving as a distributed system characterised by a high communication-to-compute ratio. It covers the three principal strategies for partitioning a model across GPUs and the communication cost associated with each.
We have Lightning Talks open this time, so feel free to bring your laptop and materials if you’d like to share something with an audience!
See you there, and let’s talk systems!
Venue
Pre6.ai
UrbanVault65, 11th Main Rd,
Sector 6, HSR Layout,
Bengaluru - 560102
Karnataka, IN
Loading…
Hosted by
Bengaluru Systems Meetup