rocm_jax/jax/experimental
jax authors e1cad34522 Add ChunkedCausalMask for Splash Attention to support attention masking similar to Llama4.
Llama4 uses (interleaved) chunk attention to support long context.

PiperOrigin-RevId: 746661156
2025-04-11 18:59:07 -07:00
..
2025-03-27 17:12:59 -07:00