41 Commits

Author	SHA1	Message	Date
Disty0	8d6bfcd827	Update SDNQ	2026-01-23 14:39:07 +03:00
Disty0	784cda80aa	update sdnq	2026-01-14 16:23:26 +03:00
Disty0	47dcab3522	update sdnq	2026-01-09 00:34:32 +03:00
Disty0	e7fa690321	cleanup	2025-12-26 20:10:55 +03:00
Disty0	4a4784eafa	SDNQ add new stack of custom floating point types and remove irrelevant qtypes from the ui list	2025-12-26 20:09:17 +03:00
Disty0	ce8b6d138c	SDNQ remove forced uint4 from convs and cleanup	2025-12-13 01:32:52 +03:00
Disty0	949ff04577	SDNQ fix fp16 mm with fp8 weights and improve stochastic rounding performance	2025-12-09 17:41:29 +03:00
Disty0	1c2a81ee2d	Make SDNQDequantizer a dataclass	2025-12-08 22:29:45 +03:00
Disty0	ed6f977218	SDNQ fix z_image matmul	2025-11-27 14:19:29 +03:00
Disty0	70b96daa63	cleanup	2025-11-25 23:02:01 +03:00
Disty0	b6e9332cfe	SDNQ de-couple matmul dtype and add fp16 matmul	2025-11-22 02:16:20 +03:00
Disty0	49cd85d388	SDNQ add training related changes	2025-11-18 22:46:14 +03:00
Disty0	3fbfae5963	cleanup	2025-11-18 02:37:10 +03:00
Disty0	1745ed53f8	Refactor SDNQDequantizer	2025-11-18 01:42:58 +03:00
Disty0	6f33ec3357	SDNQ use the model quant params instead of user settings on Lora	2025-11-10 00:12:38 +03:00
Disty0	f05c29175e	cleanup	2025-10-19 02:09:25 +03:00
Disty0	ef72edf18f	SDNQ improve svd and low bit matmul perf	2025-10-19 00:06:07 +03:00
Disty0	9206d9443e	SDNQ add dequantize model	2025-10-12 00:00:53 +03:00
Disty0	5306376b2a	improve contiguous mm performance	2025-10-06 19:05:46 +03:00
Disty0	be91bbff75	SDNQ add SVD support for Convs	2025-10-06 18:26:42 +03:00
Disty0	c931bf9efa	SDNQ add dtype casting to loader	2025-10-06 17:44:52 +03:00
Disty0	23f2deaa58	fix enable_quantized_mamtul	2025-10-06 02:04:28 +03:00
Disty0	9e52d0c1fb	SDNQ add SVDQuant quantization method	2025-10-05 22:50:30 +03:00
Disty0	f2e12a682f	SDNQ remove use_contiguous_mm path in re_quant	2025-10-04 19:17:05 +03:00
Disty0	99113947bf	SDNQ add RDNA2 INT8 support via Triton	2025-10-04 18:31:25 +03:00
Disty0	95a7da7e75	SDNQ use non-contiguous re-quantize	2025-10-03 18:54:58 +03:00
Disty0	54acf1760b	Make SDNQ scales compatible with balanced offload	2025-10-03 18:13:55 +03:00
Disty0	e6715ba8d3	Cleanup SDNQ compile	2025-09-19 19:29:36 +03:00
Disty0	a12edc1e90	SDNQ use nan_to_num_ with fp8 quantization in case of zeros	2025-09-15 20:22:39 +03:00
Disty0	4ec8603f63	SDNQ re-add bitpacking for uint1	2025-08-29 23:06:11 +03:00
Disty0	d49e954918	SDNQ listen to dequantize_fp32 option with re_quantize	2025-08-29 22:48:28 +03:00
Disty0	a8de3f7282	SDNQ add quantized matmul support for all quantization types and group sizes	2025-08-29 22:26:47 +03:00
Disty0	8460be662c	SDNQ use inplace transpose and use view instead of reshape	2025-08-17 05:07:55 +03:00
Disty0	dc7b25d387	Cleanup SDNQ and add SDNQ_USE_TENSORWISE_FP8_MATMUL env var	2025-08-11 14:50:17 +03:00
Disty0	3f45c4e570	Cleanup SDNQ and skip transpose on packed int8 matmul	2025-08-10 19:31:34 +03:00
Disty0	c3d007b02c	SDNQ split forward.py into layers and cleanup	2025-08-02 17:36:55 +03:00
Disty0	25a4731a97	SDNQ use static compile	2025-07-20 16:25:57 +03:00
Disty0	86cd272b96	SDNQ fix Dora	2025-06-18 16:24:42 +03:00
Disty0	26800a1ef9	Cleanup sdnq	2025-06-17 02:05:13 +03:00
Disty0	d31df8c1eb	SDNQ fuse bias into dequantizer with matmul	2025-06-14 22:10:10 +03:00
Disty0	5e013fb154	SDNQ optimize input quantization and use the word quantize instead of compress	2025-06-12 12:06:57 +03:00