Skip to content

[Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support) #12776

[Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support)

[Kernel] Correctly invoke prefill & decode kernels for cross-attention (towards eventual encoder/decoder model support) #12776

Annotations

2 warnings

This job succeeded