Files
stable-diffusion-webui-forge/packages_3rdparty
layerdiffusion 82dfc2b15b Significantly speed up Q4_0, Q4_1, Q4_K
by precomputing all possible 4bit dequant into a lookup table and use pytorch indexing to get dequant, rather than really computing the bit operations.
This should give very similar performance to native CUDA kernels, while being LoRA friendly and more flexiable
2024-08-25 16:49:33 -07:00
..
2024-08-13 07:13:32 -07:00

Please follow the standard of 315f85d4f4/3rdparty when PR or modifying files.