jax-flash-attn2
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).
Activity
- Latest release
- 1y ago
- Total releases
- 2
- Cadence
- ~4 months
- Last 12 months
- 0
Details
- License
- Apache-2.0
- First release
- Oct 23, 2024
Releases
| Version | Released | |
|---|---|---|
0.0.3
patch
| ||
0.0.1
initial
|