1580158
/
automatic
mirror of https://github.com/vladmandic/automatic
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
9,922 Commits
3 Branches
29 Tags
109 MiB
Commit Graph

6441 Commits (4e4557d81c57128a9d847b19463b1ed67dd7c8d8)

Author SHA1 Message Date
Disty0 4e4557d81c NNCF set min matmul shape to 32 2025-05-13 18:50:23 +03:00
Disty0 b9ad55857d NNCF INT8 MatMul don't force FP32 with FP16 scales 2025-05-13 05:08:22 +03:00
Disty0 129c701b3d NNCF use torch.compile directly on int8_matmul instead of sub functions 2025-05-13 04:28:37 +03:00
Disty0 f1eefe97a4 NNCF use inplace ops 2025-05-13 03:49:30 +03:00
Vladimir Mandic 47862fef08 prompt enhance nsfw allow/disallow 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-12 20:33:16 -04:00
Disty0 98ccce68a1
Merge branch 'master' into master 2025-05-13 03:28:51 +03:00
chrismuzyn 299d189276 When using the openvino backend, do not look for an nvidia gpu. 2025-05-12 19:14:26 -04:00
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
Vladimir Mandic a6e6c6ce5e support sdxl packaged without vae 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-11 14:49:27 -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 03d05b6243 NNCF fix very large number of groups 2025-05-11 18:43:19 +03:00
Disty0 9cfdc3c079 Remove NNCF device hijack 2025-05-11 18:30:10 +03:00
Disty0 0673689d5b NNCF set the default group size to 128 for INT4 2025-05-11 08:45:27 +03:00
Disty0 4af570bfd4 Cleanup 2025-05-11 08:10:13 +03:00
Disty0 8d27d34969 NNCF don't clip the zero_point 2025-05-11 07:57:51 +03:00
Disty0 98308fa187 NNCF fix group size calculation 2025-05-11 07:08:21 +03:00
Disty0 020e1aa374 Cleanup 2025-05-11 06:56:36 +03:00
Disty0 03a6d7f9bf NNCF add number of quantization groups 2025-05-11 05:55:58 +03:00
Vladimir Mandic 6036ff2105 modernui framepack and history tabs 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-10 10:21:37 -04:00
Vladimir Mandic aa04dd900a fix modernui disabled 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-10 08:53:30 -04:00
Vladimir Mandic f0d81ee1e0 cleanup 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-10 08:28:19 -04:00
Seunghoon Lee 6d2b5fc37c
Merge pull request #3921 from alexsarmiento/patch-1 
Update fwd_prefill.py
 2025-05-10 11:47:26 +09:00
Disty0 a1491a660c Cleanup 2025-05-09 23:36:50 +03:00
Disty0 1ee9832e05 NNCF silence the pytorch version warning 2025-05-09 23:16:55 +03:00
Disty0 b0e5a6c4df Add devices.has_triton() and enable NNCF compile if triton is available 2025-05-09 22:24:36 +03:00
AS 399a630778
Merge branch 'dev' into patch-1 2025-05-09 11:18:25 -07:00
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 51716bbaba update diffusers 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-09 09:04:21 -04:00
Vladimir Mandic 808462fdab update changelog 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-09 08:18:40 -04:00
Seunghoon Lee a27abf7363
zluda fix old cards 2025-05-09 20:02:45 +09:00
Disty0 9b641becd5 IPEX fix torch.compile with tensor.to 2025-05-09 11:07:51 +03:00
Seunghoon Lee 18f58e13f8
Update fwd_prefill.py 2025-05-09 13:36:01 +09:00
Vladimir Mandic 9e18d2f658
Merge branch 'dev' into patch-1 2025-05-08 23:21:24 -04:00
AS 5e561560ea
Update fwd_prefill.py 
Remove cudagraph from triton autotune. Buggy under zluda
 2025-05-08 19:32:51 -07:00
Vladimir Mandic 6489e4c37d prompt-enhance api support and img2img support 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-08 15:31:07 -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
Vladimir Mandic 432a5977a7 adetailer fix enable-disable 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-08 10:10:43 -04:00
Disty0 f3aa3b4574 NNCF remove T5 hijack from pre quant mode 2025-05-08 14:11:19 +03:00
Disty0 dfebc909eb Disable cuDNN benchmark on ROCm and add cudnn_benchmark_limit option 2025-05-08 13:27:06 +03:00
Vladimir Mandic 8433f685e7 clear-cache on model unload 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-07 20:22:30 -04:00
Disty0 b6d2aa7fd8 NNCF more optimizations 2025-05-07 21:50:31 +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
Vladimir Mandic 78e22350b9 add api get-checkpoint 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-07 10:31:06 -04:00
Seunghoon Lee 2a4eb86d10
zluda 3.9.4 & update flash attention 2 2025-05-07 00:39:40 +09:00
Vladimir Mandic 83fc68ece3 update requirements 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-06 09:47:13 -04:00
Vladimir Mandic 02fd0aee06 fix control refiner 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-06 09:06:50 -04:00
Vladimir Mandic 1da43e4f62 api b64 error handler 
Signed-off-by: Vladimir Mandic <mandic00@live.com>
 2025-05-05 22:28:03 -04:00