automatic/modules/sdnq
Disty0 1c2a81ee2d Make SDNQDequantizer a dataclass 2025-12-08 22:29:45 +03:00
..
layers SDNQ fix svd + fp8 tw and fp16 mm 2025-11-28 22:31:09 +03:00
__init__.py pull sdnq version from .common 2025-11-28 01:10:05 +03:00
common.py SDNQ fix torch.compile always being active 2025-12-08 18:15:08 +03:00
dequantizer.py Make SDNQDequantizer a dataclass 2025-12-08 22:29:45 +03:00
file_loader.py handle files = str case 2025-10-27 21:40:18 +03:00
forward.py SDNQ de-couple matmul dtype and add fp16 matmul 2025-11-22 02:16:20 +03:00
loader.py SDNQ fix torch.compile always being active 2025-12-08 18:15:08 +03:00
packed_int.py SDNQ Improve UINT3 and below quant speed 2025-10-05 03:12:05 +03:00
quantizer.py lint 2025-12-08 18:12:47 +01:00
triton_mm.py SDNQ de-couple matmul dtype and add fp16 matmul 2025-11-22 02:16:20 +03:00