Commit Graph

1346 Commits (4e4557d81c57128a9d847b19463b1ed67dd7c8d8)

Author SHA1 Message Date
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
Disty0 74d4093e74 NNCF disable quant conv by default 2025-04-23 16:31:27 +03:00
Vladimir Mandic 641e1e52b3 fix config save
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-23 09:10:53 -04:00
Disty0 bb0329f54f Update and refactor NNCF and add more quant options 2025-04-23 02:03:30 +03:00
Disty0 2264d8087b Pre-load support for NNCF 2025-04-22 04:35:36 +03:00
Disty0 4c5cbde1f5 Make ROCm listen to the gc config and set the minimum gc threshold to 1 2025-04-21 01:53:07 +03:00
Seunghoon Lee 712530341a
fix onnx 2025-04-19 13:25:05 +09:00
Vladimir Mandic cbef571f90 svdquant and others stuff
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-17 22:14:11 -04:00
Vladimir Mandic 75ebf1e196 hidream add llm info to metadata
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-17 14:44:37 -04:00
Vladimir Mandic 15f8e70e89 add nunchaku prototype
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-15 14:39:24 -04:00
Vladimir Mandic 59efc95e00 flux-cfgzero map autopipeline
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-14 10:03:33 -04:00
Vladimir Mandic 4aa17ca745 networks regex pattern(s) for skip-scan
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-13 09:10:11 -04:00
Vladimir Mandic 90415a7469 add cfgzero to additional pipelines
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-13 07:56:32 -04:00
Vladimir Mandic 6f2891afbd add cfgzero for flux
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-12 19:20:27 -04:00
Vladimir Mandic 3533258980 hidream whitelist samplers
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-11 22:32:57 -04:00
Vladimir Mandic 78d8bfeba7 hidream allow custom llama
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-11 21:27:48 -04:00
Vladimir Mandic 0439e5652d add shared.opts.device_map
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-11 14:53:42 -04:00
Vladimir Mandic 92af0036c6 add hidream
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-10 16:28:15 -04:00
Vladimir Mandic dc9a64d00b memmon detect gpu swapping
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-07 08:59:54 -04:00
Vladimir Mandic 84a24fb681 lora restore weights to orig device on apply
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-07 07:49:18 -04:00
Vladimir Mandic f414ea1139 set offload default
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-06 13:10:32 -04:00
Vladimir Mandic 8f95477ad2 add teacache for flux
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-05 12:58:00 -04:00
Vladimir Mandic 7520be4874 styles resize and bring quick-ui forward on hover
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-04 09:05:32 -04:00
Vladimir Mandic cd8357f1f4 add detailer renoise feature
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-03 21:12:58 -04:00
Vladimir Mandic 5bdc87b68a fix server restart
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-03 08:22:43 -04:00
Vladimir Mandic 760b41e99f update requirements and changelog
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-02 09:33:09 -04:00
Vladimir Mandic 032bd46de2 improve mp4 download
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-01 13:39:47 -04:00
Vladimir Mandic 5906eb6792 lora apply on gpu vs cpu settings option
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-04-01 13:39:47 -04:00
Vladimir Mandic daec94a9e9 settings css improvements
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-30 15:39:44 -04:00
Vladimir Mandic a467e23d72 full ui-settings refactor
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-30 15:04:17 -04:00
Vladimir Mandic f4fdd496b9 more granular quantization modules options
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-28 14:46:52 -04:00
Vladimir Mandic d1c3b97c65 add prompt enhance
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2025-03-28 14:05:28 -04:00