Skip to content

CUDA: add FP32 FlashAttention vector kernel #12040

CUDA: add FP32 FlashAttention vector kernel

CUDA: add FP32 FlashAttention vector kernel #12040

Annotations

1 warning

Push Docker image to Docker Hub (light-cuda, .devops/main-cuda.Dockerfile, linux/amd64)

succeeded May 11, 2024 in 25m 19s