59 Commits (9de84792b4c4ae644fe84df73e97ecffac01a163)

Author	SHA1	Message	Date
Disty0	a8de3f7282	SDNQ add quantized matmul support for all quantization types and group sizes	2025-08-29 22:26:47 +03:00
Disty0	dc7b25d387	Cleanup SDNQ and add SDNQ_USE_TENSORWISE_FP8_MATMUL env var	2025-08-11 14:50:17 +03:00
Disty0	c3d007b02c	SDNQ split forward.py into layers and cleanup	2025-08-02 17:36:55 +03:00
Vladimir Mandic	2656d3aa68	lint ... Signed-off-by: Vladimir Mandic <mandic00@live.com>	2025-07-24 15:42:29 -04:00
Disty0	444974a6ff	cleanup	2025-07-23 19:02:44 +03:00
Disty0	7a08e1a7f2	SDNQ always use custom tensorwise fp8 matmul	2025-07-23 19:01:10 +03:00
Disty0	e43d1d2ba7	SDNQ use strings as target_dtype	2025-06-25 23:25:49 +03:00
Disty0	33fadf946b	SDNQ add 7 bit support	2025-06-10 11:33:06 +03:00
Disty0	5eed9135e3	Split SDNQ into multiple files and linting	2025-06-10 03:18:25 +03:00