automatic/modules/sdnq at 2cd6600a386a19c5df46e03cb03b8316452aef01 - automatic - Gitea: Git with a cup of coffee

Public/automatic

mirror of https://github.com/vladmandic/automatic synced 2026-09-08 05:48:42 +02:00

Files

T

History

Disty0 ce8b6d138c SDNQ remove forced uint4 from convs and cleanup

2025-12-13 01:32:52 +03:00

..

SDNQ fix fp16 mm with fp8 weights and improve stochastic rounding performance

2025-12-09 17:41:29 +03:00

__init__.py

pull sdnq version from .common

2025-11-28 01:10:05 +03:00

common.py

SDNQ remove forced uint4 from convs and cleanup

2025-12-13 01:32:52 +03:00

dequantizer.py

SDNQ remove forced uint4 from convs and cleanup

2025-12-13 01:32:52 +03:00

file_loader.py

SDNQ remove forced uint4 from convs and cleanup

2025-12-13 01:32:52 +03:00

forward.py

SDNQ de-couple matmul dtype and add fp16 matmul

2025-11-22 02:16:20 +03:00

loader.py

SDNQ remove forced uint4 from convs and cleanup

2025-12-13 01:32:52 +03:00

packed_int.py

SDNQ Improve UINT3 and below quant speed

2025-10-05 03:12:05 +03:00

quantizer.py

SDNQ remove forced uint4 from convs and cleanup

2025-12-13 01:32:52 +03:00

triton_mm.py

SDNQ remove forced uint4 from convs and cleanup

2025-12-13 01:32:52 +03:00