1580158
/
automatic
mirror of https://github.com/vladmandic/automatic
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
10,674 Commits
3 Branches
29 Tags
109 MiB
Commit Graph

42 Commits (3af9d3bb501c1ef34bb9a2fa0df9bb75bc3830e2)

Author SHA1 Message Date
Disty0 f324b7c0e5 SDNQ remove unnecessary .contiguous() 2025-08-21 02:21:05 +03:00
Disty0 e49814098e Add sdnq_modules_dtype_dict 2025-08-20 14:58:54 +03:00
Disty0 0946710662 Add sdnq_modules_to_not_convert to UI settings 2025-08-20 04:38:20 +03:00
Disty0 47ff01fd3b SDNQ add "*" support and upcast only the first and last layer's img_mod to 6 bit with Qwen Image 2025-08-20 03:24:19 +03:00
Disty0 47154db8b1 SDNQ Flux lora, use shape from sdnq_dequantizer 2025-08-18 19:53:57 +03:00
Vladimir Mandic fc547a3ccd sdnq with diffusers lora loader 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-08-18 10:29:01 -04:00
Disty0 85d494ee84 revert .t_().contiguous().t_() 2025-08-17 05:19:44 +03:00
Disty0 8460be662c SDNQ use inplace transpose and use view instead of reshape 2025-08-17 05:07:55 +03:00
Disty0 8ca74d0cd2 SDNQ rename unused param_name arg to op 2025-08-13 22:10:30 +03:00
Disty0 cb0c5414a3 SDNQ use uint with minimum_bits <= 4 2025-08-13 00:37:44 +03:00
Disty0 7085db9add Update changelog 2025-08-13 00:17:15 +03:00
Disty0 15cb8fe9f8 SDNQ add modules_dtype_dict and fix Qwen Image with quants less than 5 bits 2025-08-13 00:07:36 +03:00
Disty0 f45e3342e6 Cleanup 2025-08-11 15:11:29 +03:00
Disty0 afb3a5a06d SDNQ move non_blocking to quant config 2025-08-11 15:07:02 +03:00
Disty0 3f45c4e570 Cleanup SDNQ and skip transpose on packed int8 matmul 2025-08-10 19:31:34 +03:00
Disty0 69db77e365 SDNQ remove eps 2025-08-09 02:39:01 +03:00
Disty0 aa0652caa9 SDNQ fix new transformers 2025-08-07 00:18:24 +03:00
Disty0 ab8badfe0d SDNQ use non-blocking ops 2025-08-06 17:07:36 +03:00
Disty0 1d5dce1fb1 cleanup 2025-08-02 17:41:53 +03:00
Disty0 c3d007b02c SDNQ split forward.py into layers and cleanup 2025-08-02 17:36:55 +03:00
Vladimir Mandic fa44521ea3 offload-never and offload-always per-module and new highvram profile 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-31 11:40:24 -04:00
Disty0 30af1f8fb0 Use inference_context with SDNQ 2025-07-14 13:07:44 +03:00
Vladimir Mandic e6d97f4d44 monkeypatch numpy for gradio 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-07 19:45:30 -04:00
Disty0 cf90e5621a Add _skip_layerwise_casting_patterns to SDNQ skip list 2025-07-04 00:04:01 +03:00
Vladimir Mandic c4d9338d2e major refactoring of modules 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-03 09:18:38 -04:00
Disty0 dc8fd006b2 Add modules_to_not_convert to pre-mode quants 2025-06-26 02:47:10 +03:00
Disty0 bbf986d3a5 Fix LTXVideo 2025-06-23 17:37:20 +03:00
Disty0 87e6d3f4fc SDNQ add modules_to_not_convert and don't quant _keep_in_fp32_modules layers in post mode 2025-06-20 20:41:11 +03:00
Disty0 7fc7797a1d SDNQ fix group size calc on odd shapes 2025-06-19 11:36:41 +03:00
Disty0 86cd272b96 SDNQ fix Dora 2025-06-18 16:24:42 +03:00
Disty0 e657cf790d SDNQ fix int8 matmul with qwen 2025-06-18 02:12:34 +03:00
Disty0 26800a1ef9 Cleanup sdnq 2025-06-17 02:05:13 +03:00
Disty0 25fc0094a9 SDNQ use quantize_device and return_device args and fix decompress_fp32 always being on 2025-06-14 21:29:08 +03:00
Disty0 c01802d9ff SDNQ fix transformers llm 2025-06-14 01:13:51 +03:00
Disty0 8f8e5ce1b0 Cleanup x2 2025-06-14 01:08:25 +03:00
Disty0 2ba64abcde Cleanup 2025-06-14 00:54:18 +03:00
Disty0 5e013fb154 SDNQ optimize input quantization and use the word quantize instead of compress 2025-06-12 12:06:57 +03:00
Disty0 2d05396b4e SDNQ simplify sym scale formula 2025-06-12 02:26:04 +03:00
Disty0 5cefa64a60 SDNQ update accepted dtypes 2025-06-11 20:58:54 +03:00
Disty0 78f99abec8 SDNQ use group_size / 2 for convs 2025-06-10 15:29:24 +03:00
Disty0 5bd7a08877 don't use inplace ops in quant layer 2025-06-10 03:29:07 +03:00
Disty0 5eed9135e3 Split SDNQ into multiple files and linting 2025-06-10 03:18:25 +03:00