PyPI page
Home page
Author:
Erfan Zare Chavoshi
License:
Apache-2.0
Summary:
Flash Attention Implementation with Multiple Backend Support and Sharding This module provides a flexible implementation of Flash Attention with support for different backends (GPU, TPU, CPU) and platforms (Triton, Pallas, JAX).
Latest version:
0.0.3
Required dependencies:
eformer
|
einops
|
jax
|
jaxlib
|
triton
Downloads last day:
2
Downloads last week:
21
Downloads last month:
66