Commit Graph

10063 Commits

Author SHA1 Message Date
Disty0 6bcd335f37 Update changelog and wiki 2025-06-05 20:17:46 +03:00
Disty0 778ca0436b Update wiki 2025-06-05 19:26:22 +03:00
Disty0 413cf54cb6 Update changelog 2025-06-05 18:11:36 +03:00
Disty0 8c03f78197 Fix bias is None 2025-06-05 14:37:00 +03:00
Disty0 1a00517338 SDNQ FP8 matmul support for Conv2d 2025-06-05 14:32:26 +03:00
Disty0 9b55ffe449 SDNQ fix VAE x2 2025-06-05 14:17:59 +03:00
Disty0 ad2a4ad616 Cleanup 2025-06-05 13:38:04 +03:00
Disty0 e25890bb1d SDNQ INT8 matmul support for Conv2d 2025-06-05 13:36:49 +03:00
Disty0 c7fb5b1690 SDNQ fix VAE quant 2025-06-05 13:24:02 +03:00
Disty0 1c508fbda4 Merge pull request #3960 from vladmandic/master
Merge pull request #3957 from vladmandic/dev
2025-06-03 18:13:47 +03:00
Disty0 0777f67573 Update changelog 2025-06-03 18:12:12 +03:00
Disty0 ce3a6e27fa SDNQ use channelwise only quant 2025-06-03 12:30:19 +03:00
Disty0 79ec23dd9d SDNQ override conv dtype 2025-06-03 02:37:29 +03:00
Disty0 e9ff242e03 SDNQ add group size support for convs 2025-06-03 02:16:52 +03:00
Disty0 6f637f41cc Use tensorwise fp8 matmul with torch < 2.5 2025-06-02 23:28:49 +03:00
Disty0 3f3a986c0e SDNQ fix scale staying in fp32 with tensorwise fp8 matmul 2025-06-02 23:18:28 +03:00
Vladimir Mandic 3ca9f29c8f Merge pull request #3957 from vladmandic/dev
merge dev
2025-06-02 15:52:22 +02:00
Vladimir Mandic 7d05bed459 update changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-02 15:50:42 +02:00
Vladimir Mandic f147bca20f Merge branch 'master' into dev 2025-06-02 15:45:38 +02:00
Vladimir Mandic b1d6897621 update changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-02 15:44:52 +02:00
Disty0 4e3795a0a5 SDNQ fix packed int8 matmul 2025-06-02 03:31:51 +03:00
Disty0 82f5634d53 SDNQ use torch.bool for uint1 2025-06-02 01:39:51 +03:00
Disty0 ea7fe3bb73 OpenVINO update dtype_mapping 2025-06-02 01:11:41 +03:00
Disty0 e8588c91ea SDNQ enable matmul support for float8_e5m2 2025-06-02 00:53:10 +03:00
Disty0 8f1a1d7311 SDNQ expand quantized_matmul_dtypes for CPU 2025-06-02 00:28:29 +03:00
Disty0 b146025a5e SDNQ add int2 2025-06-02 00:17:39 +03:00
Disty0 766aec32d5 Update changelog 2025-06-01 23:35:00 +03:00
Disty0 9669b36010 SDNQ fix older PyTorch with FP8 matmul 2025-06-01 23:29:16 +03:00
Disty0 acefa58834 SDNQ don't force fp32 with fp8 tensorwise matmul 2025-06-01 23:16:00 +03:00
Disty0 839295f79a Add fp8 fnuz to sdnq options 2025-06-01 23:10:08 +03:00
Vladimir Mandic c77162fb82 update wiki and changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-06-01 21:31:43 +02:00
Disty0 539fae3234 Update naming 2025-06-01 21:01:56 +03:00
Disty0 cefe460052 SDNQ skip FP8 matmul for input len < 32 2025-05-31 01:27:59 +03:00
Disty0 046840c8be Fix HiDream sampling 2025-05-31 00:52:56 +03:00
Disty0 109c0d7e49 SDNQ use tensorwise FP8 matmul on CPU 2025-05-30 21:09:53 +03:00
Disty0 959b759721 Cleanup 2025-05-30 16:45:59 +03:00
Disty0 b5d588fa45 SDNQ remove unnecessary bitwise ands 2025-05-30 16:29:59 +03:00
Disty0 db816d7088 Cleanup 2025-05-30 16:02:26 +03:00
Disty0 c85cc6b397 SDNQ enable quant with GPU by default and don't do unnecessary clones 2025-05-30 15:21:29 +03:00
Disty0 4654acde3c SDNQ re-enable memory fix for diffusers 2025-05-30 14:59:45 +03:00
Disty0 87a801e24d SDNQ remove memory fix hijack 2025-05-30 13:54:49 +03:00
Disty0 f81cb22c00 SDNQ fix new transformers 2025-05-30 13:32:03 +03:00
Disty0 36febda6e6 SDNQ update supported dtypes 2025-05-30 13:07:23 +03:00
Disty0 29bd2af779 SDNQ add 6-bit support 2025-05-30 12:20:13 +03:00
Vladimir Mandic 98a11fc86c fix gallery duplicate entries
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-05-30 11:04:56 +02:00
Vladimir Mandic 9168a66fd2 update requirements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-05-30 08:53:39 +02:00
Vladimir Mandic 4e184f41af update changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-05-30 08:44:30 +02:00
Disty0 d1491962d9 One bit 2025-05-30 05:41:02 +03:00
Disty0 3c8be0f55f SDNQ add uint2 2025-05-30 04:47:29 +03:00
Disty0 599224d392 SDNQ reduce 5 reshape ops to 2 with quantized input 2025-05-30 01:31:41 +03:00