patientx
5a425aeda1
Merge branch 'comfyanonymous:master' into master
2024-10-20 21:06:24 +03:00
comfyanonymous
471cd3eace
fp8 casting is fast on GPUs that support fp8 compute.
2024-10-20 00:54:47 -04:00
patientx
d4b509799f
Merge branch 'comfyanonymous:master' into master
2024-10-18 11:14:20 +03:00
comfyanonymous
67158994a4
Use the lowvram cast_to function for everything.
2024-10-17 17:25:56 -04:00
patientx
f9eab05f54
Merge branch 'comfyanonymous:master' into master
2024-10-10 10:30:17 +03:00
Jonathan Avila
4b2f0d9413
Increase maximum macOS version to 15.0.1 when forcing upcast attention ( #5191 )
2024-10-09 22:21:41 -04:00
comfyanonymous
e38c94228b
Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node.
...
This is used to load weights in fp8 and use fp8 matrix multiplication.
2024-10-09 19:43:17 -04:00
patientx
ae611c9b61
Merge branch 'comfyanonymous:master' into master
2024-09-21 13:51:37 +03:00
comfyanonymous
dc96a1ae19
Load controlnet in fp8 if weights are in fp8.
2024-09-21 04:50:12 -04:00
patientx
9e8686df8d
Merge branch 'comfyanonymous:master' into master
2024-09-19 19:57:21 +03:00
Simon Lui
de8e8e3b0d
Fix xpu Pytorch nightly build from calling optimize which doesn't exist. ( #4978 )
2024-09-19 05:11:42 -04:00
patientx
6fdbaf1a76
Merge branch 'comfyanonymous:master' into master
2024-09-05 12:04:05 +03:00
comfyanonymous
c7427375ee
Prioritize freeing partially offloaded models first.
2024-09-04 19:47:32 -04:00
patientx
894c727ce2
Update model_management.py
2024-09-05 00:05:54 +03:00
patientx
93fa5c9ebb
Merge branch 'comfyanonymous:master' into master
2024-09-02 10:03:48 +03:00
comfyanonymous
8d31a6632f
Speed up inference on nvidia 10 series on Linux.
2024-09-01 17:29:31 -04:00
patientx
f02c0d3ed9
Merge branch 'comfyanonymous:master' into master
2024-09-01 14:34:56 +03:00
comfyanonymous
b643eae08b
Make minimum_inference_memory() depend on --reserve-vram
2024-09-01 01:18:34 -04:00
patientx
acc3d6a2ea
Update model_management.py
2024-08-30 20:13:28 +03:00
patientx
51af2440ef
Update model_management.py
2024-08-30 20:10:47 +03:00
patientx
3e226f02f3
Update model_management.py
2024-08-30 20:08:18 +03:00
comfyanonymous
935ae153e1
Cleanup.
2024-08-30 12:53:59 -04:00
patientx
7056a6aa6f
Merge branch 'comfyanonymous:master' into master
2024-08-28 09:36:30 +03:00
comfyanonymous
38c22e631a
Fix case where model was not properly unloaded in merging workflows.
2024-08-27 19:03:51 -04:00
patientx
134569ea48
Update model_management.py
2024-08-23 14:10:09 +03:00
patientx
c98e8a0a55
Merge branch 'comfyanonymous:master' into master
2024-08-23 12:31:51 +03:00
comfyanonymous
5d8bbb7281
Cleanup.
2024-08-23 04:06:27 -04:00
patientx
9f87d61bfe
Merge branch 'comfyanonymous:master' into master
2024-08-23 11:04:56 +03:00
comfyanonymous
2c1d2375d6
Fix.
2024-08-23 04:04:55 -04:00
Simon Lui
64ccb3c7e3
Rework IPEX check for future inclusion of XPU into Pytorch upstream and do a bit more optimization of ipex.optimize(). ( #4562 )
2024-08-23 03:59:57 -04:00
patientx
1ef90b7ac8
Merge branch 'comfyanonymous:master' into master
2024-08-23 00:55:19 +03:00
comfyanonymous
7c6bb84016
Code cleanups.
2024-08-22 17:05:12 -04:00
patientx
dec75f11e4
Merge branch 'comfyanonymous:master' into master
2024-08-22 23:36:58 +03:00
comfyanonymous
c54d3ed5e6
Fix issue with models staying loaded in memory.
2024-08-22 15:58:20 -04:00
David
7b70b266d8
Generalize MacOS version check for force-upcast-attention ( #4548 )
...
This code automatically forces upcasting attention for MacOS versions 14.5 and 14.6. My computer returns the string "14.6.1" for `platform.mac_ver()[0]`, so this generalizes the comparison to catch more versions.
I am running MacOS Sonoma 14.6.1 (latest version) and was seeing black image generation on previously functional workflows after recent software updates. This PR solved the issue for me.
See comfyanonymous/ComfyUI#3521
2024-08-22 13:24:21 -04:00
patientx
0cd8a740bb
Merge branch 'comfyanonymous:master' into master
2024-08-22 14:01:42 +03:00
comfyanonymous
843a7ff70c
fp16 is actually faster than fp32 on a GTX 1080.
2024-08-21 23:23:50 -04:00
patientx
febf8601dc
Merge branch 'comfyanonymous:master' into master
2024-08-22 00:07:14 +03:00
comfyanonymous
a60620dcea
Fix slow performance on 10 series Nvidia GPUs.
2024-08-21 16:39:02 -04:00
patientx
ac75d4e4e0
Merge branch 'comfyanonymous:master' into master
2024-08-21 09:49:29 +03:00
comfyanonymous
03ec517afb
Remove useless line, adjust windows default reserved vram.
2024-08-21 00:47:19 -04:00
patientx
5656b5b956
Merge branch 'comfyanonymous:master' into master
2024-08-20 23:07:54 +03:00
comfyanonymous
9953f22fce
Add --fast argument to enable experimental optimizations.
...
Optimizations that might break things/lower quality will be put behind
this flag first and might be enabled by default in the future.
Currently the only optimization is float8_e4m3fn matrix multiplication on
4000/ADA series Nvidia cards or later. If you have one of these cards you
will see a speed boost when using fp8_e4m3fn flux for example.
2024-08-20 11:55:51 -04:00
comfyanonymous
1b3eee672c
Fix potential issue with multi devices.
2024-08-20 10:46:36 -04:00
patientx
b20f5b1e32
Merge branch 'comfyanonymous:master' into master
2024-08-20 00:31:41 +03:00
comfyanonymous
045377ea89
Add a --reserve-vram argument if you don't want comfy to use all of it.
...
--reserve-vram 1.0 for example will make ComfyUI try to keep 1GB vram free.
This can also be useful if workflows are failing because of OOM errors but
in that case please report it if --reserve-vram improves your situation.
2024-08-19 17:16:18 -04:00
comfyanonymous
be0726c1ed
Remove duplication.
2024-08-19 15:26:50 -04:00
patientx
7bd86b0896
Update model_management.py
2024-08-16 00:53:38 +03:00
comfyanonymous
39fb74c5bd
Fix bug when model cannot be partially unloaded.
2024-08-13 03:57:55 -04:00
comfyanonymous
74e124f4d7
Fix some issues with TE being in lowvram mode.
2024-08-12 23:42:21 -04:00
