honglyua
0ccc88b03f
Support Iluvatar CoreX ( #8585 )
...
* Support Iluvatar CoreX
Co-authored-by: mingjiang.li <mingjiang.li@iluvatar.com>
2025-07-24 13:57:36 -04:00
comfyanonymous
d3504e1778
Enable pytorch attention by default for gfx1201 on torch 2.8 ( #9029 )
2025-07-23 19:21:29 -04:00
comfyanonymous
a86a58c308
Fix xpu function not implemented p2. ( #9027 )
2025-07-23 18:18:20 -04:00
comfyanonymous
39dda1d40d
Fix xpu function not implemented. ( #9026 )
2025-07-23 18:10:59 -04:00
comfyanonymous
5ad33787de
Add default device argument. ( #9023 )
2025-07-23 14:20:49 -04:00
Simon Lui
255f139863
Add xpu version for async offload and some other things. ( #9004 )
2025-07-22 15:20:09 -04:00
comfyanonymous
a96e65df18
Disable omnigen2 fp16 on older pytorch versions. ( #8672 )
2025-06-26 03:39:09 -04:00
comfyanonymous
6e28a46454
Apple most likely is never fixing the fp16 attention bug. ( #8485 )
2025-06-10 13:06:24 -04:00
comfyanonymous
7f800d04fa
Enable AMD fp8 and pytorch attention on some GPUs. ( #8474 )
...
Information is from the pytorch source code.
2025-06-09 12:50:39 -04:00
comfyanonymous
97755eed46
Enable fp8 ops by default on gfx1201 ( #8464 )
2025-06-08 14:15:34 -04:00
comfyanonymous
daf9d25ee2
Cleaner torch version comparisons. ( #8453 )
2025-06-07 10:01:15 -04:00
comfyanonymous
704fc78854
Put ROCm version in tuple to make it easier to enable stuff based on it. ( #8348 )
2025-05-30 15:41:02 -04:00
comfyanonymous
89a84e32d2
Disable initial GPU load when novram is used. ( #8294 )
2025-05-26 16:39:27 -04:00
comfyanonymous
e5799c4899
Enable pytorch attention by default on AMD gfx1151 ( #8282 )
2025-05-26 04:29:25 -04:00
comfyanonymous
0b50d4c0db
Add argument to explicitly enable fp8 compute support. ( #8257 )
...
This can be used to test if your current GPU/pytorch version supports fp8 matrix mult in combination with --fast or the fp8_e4m3fn_fast dtype.
2025-05-23 17:43:50 -04:00
comfyanonymous
0a66d4b0af
Per device stream counters for async offload. ( #7873 )
2025-04-29 20:28:52 -04:00
comfyanonymous
5a50c3c7e5
Fix stream priority to support older pytorch. ( #7856 )
2025-04-28 13:07:21 -04:00
comfyanonymous
c8cd7ad795
Use stream for casting if enabled. ( #7833 )
2025-04-27 05:38:11 -04:00
comfyanonymous
0dcc75ca54
Add experimental --async-offload lowvram weight offloading. ( #7820 )
...
This should speed up the lowvram mode a bit. It currently is only enabled when --async-offload is used but it will be enabled by default in the future if there are no problems.
2025-04-26 16:11:21 -04:00
comfyanonymous
2d6805ce57
Add option for using fp8_e8m0fnu for model weights. ( #7733 )
...
Seems to break every model I have tried but worth testing?
2025-04-22 06:17:38 -04:00
BiologicalExplosion
2222cf67fd
MLU memory optimization ( #7470 )
...
Co-authored-by: huzhan <huzhan@cambricon.com>
2025-04-02 19:24:04 -04:00
BVH
301e26b131
Add option to store TE in bf16 ( #7461 )
2025-04-01 13:48:53 -04:00
comfyanonymous
8edc1f44c1
Support more float8 types.
2025-03-25 05:23:49 -04:00
FeepingCreature
7aceb9f91c
Add --use-flash-attention flag. ( #7223 )
...
* Add --use-flash-attention flag.
This is useful on AMD systems, as FA builds are still 10% faster than Pytorch cross-attention.
2025-03-14 03:22:41 -04:00
comfyanonymous
35504e2f93
Fix.
2025-03-13 15:03:18 -04:00
comfyanonymous
299436cfed
Print mac version.
2025-03-13 10:05:40 -04:00
comfyanonymous
0952569493
Fix stable cascade VAE on some lowvram machines.
2025-03-08 20:24:04 -05:00
Chenlei Hu
4d55f16ae8
Use enum list for --fast options ( #7024 )
2025-03-01 02:37:35 -05:00
comfyanonymous
cf0b549d48
--fast now takes a number as argument to indicate how fast you want it.
...
The idea is that you can indicate how much quality vs speed you want.
At the moment:
--fast 2 enables fp16 accumulation if your pytorch supports it.
--fast 5 enables fp8 matrix mult on fp8 models and the optimization above.
--fast without a number enables all optimizations.
2025-02-28 02:48:20 -05:00
comfyanonymous
eb4543474b
Use fp16 for intermediate for fp8 weights with --fast if supported.
2025-02-28 02:17:50 -05:00
comfyanonymous
1804397952
Use fp16 if checkpoint weights are fp16 and the model supports it.
2025-02-27 16:39:57 -05:00
BiologicalExplosion
89253e9fe5
Support Cambricon MLU ( #6964 )
...
Co-authored-by: huzhan <huzhan@cambricon.com>
2025-02-26 20:45:13 -05:00
comfyanonymous
96d891cb94
Speedup on some models by not upcasting bfloat16 to float32 on mac.
2025-02-24 05:41:32 -05:00
comfyanonymous
ace899e71a
Prioritize fp16 compute when using allow_fp16_accumulation
2025-02-23 04:45:54 -05:00
comfyanonymous
072db3bea6
Assume the mac black image bug won't be fixed before v16.
2025-02-21 20:24:07 -05:00
comfyanonymous
a6deca6d9a
Latest mac still has the black image bug.
2025-02-21 20:14:30 -05:00
comfyanonymous
41c30e92e7
Let all model memory be offloaded on nvidia.
2025-02-21 06:32:21 -05:00
comfyanonymous
12da6ef581
Apparently directml supports fp16.
2025-02-20 09:30:24 -05:00
comfyanonymous
b07258cef2
Fix typo.
...
Let me know if this slows things down on 2000 series and below.
2025-02-18 07:28:33 -05:00
comfyanonymous
31e54b7052
Improve AMD arch detection.
2025-02-17 04:53:40 -05:00
comfyanonymous
8c0bae50c3
bf16 manual cast works on old AMD.
2025-02-17 04:42:40 -05:00
comfyanonymous
530412cb9d
Refactor torch version checks to be more future proof.
2025-02-17 04:36:45 -05:00
comfyanonymous
e2919d38b4
Disable bf16 on AMD GPUs that don't support it.
2025-02-16 05:46:10 -05:00
comfyanonymous
1cd6cd6080
Disable pytorch attention in VAE for AMD.
2025-02-14 05:42:14 -05:00
comfyanonymous
d7b4bf21a2
Auto enable mem efficient attention on gfx1100 on pytorch nightly 2.7
...
I'm not not sure which arches are supported yet. If you see improvements in
memory usage while using --use-pytorch-cross-attention on your AMD GPU let
me know and I will add it to the list.
2025-02-14 04:18:14 -05:00
comfyanonymous
8773ccf74d
Better memory estimation for ROCm that support mem efficient attention.
...
There is no way to check if the card actually supports it so it assumes
that it does if you use --use-pytorch-cross-attention with yours.
2025-02-13 08:32:36 -05:00
comfyanonymous
1d5d6586f3
Fix ruff.
2025-02-12 06:49:16 -05:00
zhoufan2956
35740259de
mix_ascend_bf16_infer_err ( #6794 )
2025-02-12 06:48:11 -05:00
HishamC
b124256817
Fix for running via DirectML ( #6542 )
...
* Fix for running via DirectML
Fix DirectML empty image generation issue with Flux1. add CPU fallback for unsupported path. Verified the model works on AMD GPUs
* fix formating
* update casual mask calculation
2025-02-11 17:11:32 -05:00
comfyanonymous
af4b7c91be
Make --force-fp16 actually force the diffusion model to be fp16.
2025-02-11 08:33:09 -05:00
catboxanon
43a74c0de1
Allow FP16 accumulation with --fast ( #6453 )
...
Currently only applies to PyTorch nightly releases. (>=20250208)
2025-02-08 17:00:56 -05:00
comfyanonymous
255edf2246
Lower minimum ratio of loaded weights on Nvidia.
2025-01-27 05:26:51 -05:00
comfyanonymous
67feb05299
Remove redundant code.
2025-01-25 19:04:53 -05:00
comfyanonymous
d45ebb63f6
Remove old unused function.
2025-01-04 07:20:54 -05:00
comfyanonymous
9e9c8a1c64
Clear cache as often on AMD as Nvidia.
...
I think the issue this was working around has been solved.
If you notice that this change slows things down or causes stutters on
your AMD GPU with ROCm on Linux please report it.
2025-01-02 08:44:16 -05:00
comfyanonymous
160ca08138
Use python 3.9 in launch test instead of 3.8
...
Fix ruff check.
2024-12-26 20:05:54 -05:00
Huazhong Ji
c4bfdba330
Support ascend npu ( #5436 )
...
* support ascend npu
Co-authored-by: YukMingLaw <lymmm2@163.com>
Co-authored-by: starmountain1997 <guozr1997@hotmail.com>
Co-authored-by: Ginray <ginray0215@gmail.com>
2024-12-26 19:36:50 -05:00
comfyanonymous
19a64d6291
Cleanup some mac related code.
2024-12-25 05:32:51 -05:00
comfyanonymous
b486885e08
Disable bfloat16 on older mac.
2024-12-25 05:18:50 -05:00
comfyanonymous
0229228f3f
Clean up the VAE dtypes code.
2024-12-25 04:50:34 -05:00
comfyanonymous
15564688ed
Add a try except block so if torch version is weird it won't crash.
2024-12-23 03:22:48 -05:00
Simon Lui
c6b9c11ef6
Add oneAPI device selector for xpu and some other changes. ( #6112 )
...
* Add oneAPI device selector and some other minor changes.
* Fix device selector variable name.
* Flip minor version check sign.
* Undo changes to README.md.
2024-12-23 03:18:32 -05:00
comfyanonymous
e44d0ac7f7
Make --novram completely offload weights.
...
This flag is mainly used for testing the weight offloading, it shouldn't
actually be used in practice.
Remove useless import.
2024-12-23 01:51:08 -05:00
comfyanonymous
57f330caf9
Relax minimum ratio of weights loaded in memory on nvidia.
...
This should make it possible to do higher res images/longer videos by
further offloading weights to CPU memory.
Please report an issue if this slows down things on your system.
2024-12-22 03:06:37 -05:00
Chenlei Hu
d7969cb070
Replace print with logging ( #6138 )
...
* Replace print with logging
* nit
* nit
* nit
* nit
* nit
* nit
2024-12-20 16:24:55 -05:00
comfyanonymous
2dda7c11a3
More proper fix for the memory issue.
2024-12-19 16:21:56 -05:00
comfyanonymous
3ad3248ad7
Fix lowvram bug when using a model multiple times in a row.
...
The memory system would load an extra 64MB each time until either the
model was completely in memory or OOM.
2024-12-19 16:04:56 -05:00
comfyanonymous
37e5390f5f
Add: --use-sage-attention to enable SageAttention.
...
You need to have the library installed first.
2024-12-18 01:56:10 -05:00
Chenlei Hu
d9d7f3c619
Lint all unused variables ( #5989 )
...
* Enable F841
* Autofix
* Remove all unused variable assignment
2024-12-12 17:59:16 -05:00
comfyanonymous
fd5dfb812c
Set initial load devices for te and model to mps device on mac.
2024-12-12 06:00:31 -05:00
comfyanonymous
57e8bf6a9f
Fix case where a memory leak could cause crash.
...
Now the only symptom of code messing up and keeping references to a model
object when it should not will be endless prints in the log instead of the
next workflow crashing ComfyUI.
2024-12-02 19:49:49 -05:00
comfyanonymous
79d5ceae6e
Improved memory management. ( #5450 )
...
* Less fragile memory management.
* Fix issue.
* Remove useless function.
* Prevent and detect some types of memory leaks.
* Run garbage collector when switching workflow if needed.
* Fix issue.
2024-12-02 14:39:34 -05:00
comfyanonymous
61196d8857
Add option to inference the diffusion model in fp32 and fp64.
2024-11-25 05:00:23 -05:00
comfyanonymous
1af4a47fd1
Bump up mac version for attention upcast bug workaround.
2024-10-31 15:15:31 -04:00
comfyanonymous
471cd3eace
fp8 casting is fast on GPUs that support fp8 compute.
2024-10-20 00:54:47 -04:00
comfyanonymous
67158994a4
Use the lowvram cast_to function for everything.
2024-10-17 17:25:56 -04:00
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
comfyanonymous
dc96a1ae19
Load controlnet in fp8 if weights are in fp8.
2024-09-21 04:50:12 -04:00
Simon Lui
de8e8e3b0d
Fix xpu Pytorch nightly build from calling optimize which doesn't exist. ( #4978 )
2024-09-19 05:11:42 -04:00
comfyanonymous
c7427375ee
Prioritize freeing partially offloaded models first.
2024-09-04 19:47:32 -04:00
comfyanonymous
8d31a6632f
Speed up inference on nvidia 10 series on Linux.
2024-09-01 17:29:31 -04:00
comfyanonymous
b643eae08b
Make minimum_inference_memory() depend on --reserve-vram
2024-09-01 01:18:34 -04:00
comfyanonymous
935ae153e1
Cleanup.
2024-08-30 12:53:59 -04:00
comfyanonymous
38c22e631a
Fix case where model was not properly unloaded in merging workflows.
2024-08-27 19:03:51 -04:00
comfyanonymous
5d8bbb7281
Cleanup.
2024-08-23 04:06:27 -04:00
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
comfyanonymous
7c6bb84016
Code cleanups.
2024-08-22 17:05:12 -04:00
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
comfyanonymous
843a7ff70c
fp16 is actually faster than fp32 on a GTX 1080.
2024-08-21 23:23:50 -04:00
comfyanonymous
a60620dcea
Fix slow performance on 10 series Nvidia GPUs.
2024-08-21 16:39:02 -04:00
comfyanonymous
03ec517afb
Remove useless line, adjust windows default reserved vram.
2024-08-21 00:47:19 -04:00
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
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
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
