14 Commits

Author	SHA1	Message	Date
Disty0	2c44dca2be	reduce warp range	2026-06-24 13:23:00 +03:00
Disty0	72a4d2c2bd	Add Hadamard support to SDNQ Atten	2026-06-23 14:17:34 +03:00
Disty0	440aa0d105	typing	2026-06-19 03:28:09 +03:00
Disty0	bd3eac047f	SDNQ fix NPU accuracy	2026-06-19 02:59:21 +03:00
Disty0	55f811e837	SDNQ add N4 Hadamard and set Hadamard Group Size to 256	2026-06-13 00:56:50 +03:00
Disty0	e5249c7a4b	Cleanup SDNQ	2026-06-07 16:14:52 +03:00
Vladimir Mandic	1f24513507	optimize sdnq quant-on-load and add platform stats ... Signed-off-by: Vladimir Mandic <mandic00@live.com>	2026-06-07 11:43:46 +02:00
Disty0	1377495998	lint	2026-05-22 18:21:22 +03:00
Disty0	e484850e9e	Cleanup SDNQ	2026-05-22 17:32:41 +03:00
Disty0	cad5ab19c8	SDNQ use torch.compile friendly hadamard cache	2026-05-19 22:18:58 +03:00
Disty0	a896719713	Fix dynamic quant with svd + hadamard combination	2026-05-18 23:31:18 +03:00
Disty0	65b9c8803f	SDNQ use cache for hadamard matrix	2026-05-18 18:20:32 +03:00
Disty0	c227d5fa10	SDNQ add Hadamard Rotation support	2026-05-18 17:06:11 +03:00
Disty0	6eebf2566d	Refactor SDNQ quantizer handling and add modules_to_not_use_matmul	2026-05-15 05:47:32 +03:00