1580158
/
automatic
mirror of https://github.com/vladmandic/automatic
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
10,241 Commits
3 Branches
29 Tags
109 MiB
Commit Graph

1377 Commits (b9d09532e5dacd104a8b129e6087f010dbc3495b)

Author SHA1 Message Date
Vladimir Mandic 7736382028 major requirements refactor 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-07-01 13:12:21 -04:00
Vladimir Mandic 4c43c1cc5e update cuda max memory limit 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-06-30 16:49:43 -04:00
Vladimir Mandic bff75f0db3 add omnigen2 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-06-27 20:20:43 -04:00
Disty0 71f7474de2 Unify quant options 2025-06-27 21:05:14 +03:00
Disty0 3b8ced444c Add auto quantization mode 2025-06-27 18:54:15 +03:00
Vladimir Mandic 42b3e08e65 Control add setting to run hires with or without control 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-06-25 18:43:29 -04:00
Vladimir Mandic 5b486a6ef1 sdnq add xyz grid support, improve offloading compatibility 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-06-25 15:32:37 -04:00
Disty0 cb4684cbeb SNDQ add separate quant mode option for Text Encoders 2025-06-13 12:42:57 +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 33fadf946b SDNQ add 7 bit support 2025-06-10 11:33:06 +03:00
Disty0 58b646e7f2 SDNQ add 5-bit and 3-bit quantization support 2025-06-10 01:48:51 +03:00
Disty0 2ccc76ab91 Increase medvram mode to 12 GB and update wiki 2025-06-06 15:27:30 +03:00
Disty0 e25890bb1d SDNQ INT8 matmul support for Conv2d 2025-06-05 13:36:49 +03:00
Disty0 b146025a5e SDNQ add int2 2025-06-02 00:17:39 +03:00
Disty0 839295f79a Add fp8 fnuz to sdnq options 2025-06-01 23:10:08 +03:00
Disty0 539fae3234 Update naming 2025-06-01 21:01:56 +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 29bd2af779 SDNQ add 6-bit support 2025-05-30 12:20:13 +03:00
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 d8e8f47ce5 SDNQ add an option to toggle quantize with GPU 2025-05-28 15:18:39 +03:00
Disty0 1961e88c13 Set SDPA as the default on all backends and enable Dyn SDPA on ROCm, DML, CPU and MPS 2025-05-28 13:42:29 +03:00
Disty0 b724cd7c57 Update changelog 2025-05-27 21:21:42 +03:00
Disty0 5d3c1832b2 SDNQ add FP8 quants 2025-05-27 20:29:15 +03:00
Disty0 dece497f10 Refactor SDNQ to use weights_dtype and rename decompress_int8_matmul to use_quantized_matmul 2025-05-27 15:49:21 +03:00
Disty0 79bb348927 SDNQ sort quant schemes by recommended order 2025-05-27 13:06:17 +03:00
Disty0 ccf9deaf28 Move SDNQ to the top of the settings list 2025-05-26 18:30:50 +03:00
Disty0 4453efee76 Rename NNCF to SDNQ and rename quant schemes 2025-05-26 02:39:51 +03:00
Disty0 85f00f9edb Enable dyn atten by default for ROCm 2025-05-23 18:24:50 +03:00
Vladimir Mandic 4157336238 rename vae 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-15 08:59:49 -04:00
Disty0 18c10883b8 Move NNCF above in the settings list 2025-05-14 05:19:11 +03:00
Disty0 f4e3a81a84 NNCF experimental direct INT8 MatMul support 2025-05-12 21:41:49 +03:00
Vladimir Mandic 91080f349f latent-diffusion-upscale n-steps 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-12 11:12:36 -04:00
Disty0 4eedeab9f8 NNCF use group size instead of number of groups and set default group size for int4 to 64 2025-05-11 20:38:01 +03:00
Disty0 0673689d5b NNCF set the default group size to 128 for INT4 2025-05-11 08:45:27 +03:00
Disty0 03a6d7f9bf NNCF add number of quantization groups 2025-05-11 05:55:58 +03:00
Disty0 b0e5a6c4df Add devices.has_triton() and enable NNCF compile if triton is available 2025-05-09 22:24:36 +03:00
Disty0 a4d4462e2a NNCF add decompress using toch.compile option 2025-05-09 21:02:24 +03:00
Seunghoon Lee 45c0bd6ec6
basic windows native pytorch support 2025-05-09 22:23:07 +09:00
Vladimir Mandic 808462fdab update changelog 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-09 08:18:40 -04:00
Vladimir Mandic 55b1cb8c8b lower default teacache threshold 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-08 10:14:15 -04:00
Disty0 dfebc909eb Disable cuDNN benchmark on ROCm and add cudnn_benchmark_limit option 2025-05-08 13:27:06 +03:00
Disty0 a57c7087b8 Make NNCF INT4 quant run 75% faster and don't force fp32 decompress 2025-05-07 20:34:07 +03:00
Vladimir Mandic 5261c55890 fix lora legacy disabled 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-07 11:48:21 -04:00
Disty0 f4dfe20bc1 Add sigmoid beta scheduler 2025-05-04 17:42:22 +03:00
Vladimir Mandic 473f394f97 fix save style 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-04-30 09:18:41 -04:00
Vladimir Mandic ff649291b5 lint fixes 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-04-28 10:55:21 -04:00
Vladimir Mandic 1b341dd809 setting to enable/disable clip skip editing 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-04-28 09:44:51 -04:00
Vladimir Mandic 5b68979226 update option names 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-04-26 13:46:33 -04:00
Vladimir Mandic 5647d782f8 configurable restore metadata settings and params 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-04-26 10:45:49 -04:00