| ▲ | 0-_-0 5 hours ago | |
32 bits vs 4 bits it looks like | ||
| ▲ | mxfeinberg 2 hours ago | parent [-] | |
Yup, and unlike the original turboquant paper, my implementation is pinned to using a 4 bit code book so I could use SIMD kernels for performance. | ||
| ▲ | 0-_-0 5 hours ago | |
32 bits vs 4 bits it looks like | ||
| ▲ | mxfeinberg 2 hours ago | parent [-] | |
Yup, and unlike the original turboquant paper, my implementation is pinned to using a 4 bit code book so I could use SIMD kernels for performance. | ||