The Dojo System Is Built to Accelerate Parallelism Models

The dojo system was built to make such models work at high utilization. A slice of the dojo mesh can be carved out to run any model. The only thing users need to do is to make the slice large enough to fit a batch norm surface for their particular model. After that the partition presents itself as one large accelerator freeing the users from having to worry about internal details of execution.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.