Topic

Video Generation

1 post about Video Generation. Every summary links to the original.

Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.

Newest first

Posts

AWS
A kernel-centric path to real-time video generation on Trainium
Reactor and the AWS Neuron Science team collaborated to optimize real-time video generation on AWS Trainium. They focused on autoregressive diffusion models, which combine sequential next-token prediction with iterative diffusion to generate video frames that respond to user input. The teams used the Rolling Forcing model as a proxy, addressing challenges such as dynamic shapes, unusual memory access patterns, and heavy cache management that generic compilers struggle with. Optimizations included splitting SDPA heads across four cores and sequences across two, and batching common components of the diffusion and cache update phases to improve hardware utilization. The collaboration achieved real-time video generation above 16 frames per second on a single Trainium2 chip, a result that generalizes across autoregressive diffusion models.

The best engineering reads, once a week.

Topic

1 post about Video Generation. Every summary links to the original.

Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.

Newest first

AWS
A kernel-centric path to real-time video generation on Trainium
Reactor and the AWS Neuron Science team collaborated to optimize real-time video generation on AWS Trainium. They focused on autoregressive diffusion models, which combine sequential next-token prediction with iterative diffusion to generate video frames that respond to user input. The teams used the Rolling Forcing model as a proxy, addressing challenges such as dynamic shapes, unusual memory access patterns, and heavy cache management that generic compilers struggle with. Optimizations included splitting SDPA heads across four cores and sequences across two, and batching common components of the diffusion and cache update phases to improve hardware utilization. The collaboration achieved real-time video generation above 16 frames per second on a single Trainium2 chip, a result that generalizes across autoregressive diffusion models.

The best engineering reads, once a week.