Flash Attention CUTE (CUDA Template Engine) implementation
Helpful tools and examples for working with flex-attention
CuTe DSL distributed mixture-of-experts kernels for PyTorch
A place to store reusable transformer components found around the interwebs
Flash Attention CUTE - package coming soon
Anthropic, PBC
Visionary sponsor
Bloomberg
Visionary sponsor
Hudson River Trading
Visionary sponsor
Meta
Visionary sponsor
NVIDIA
Visionary sponsor
Microsoft
Sustainability sponsor
Depot
Continuous Integration
AWS
Cloud computing and Security Sponsor
Datadog
Monitoring
Fastly
CDN
Google
Download Analytics
Sentry
Error logging
StatusPage
Status page