comfyanonymous
367f84be8d
Don't automatically switch to lowvram mode on GPUs with low memory.
2024-05-17 00:31:32 -04:00
Simon Lui
4cd1bc2cce
Fix Intel GPU memory allocation accuracy and documentation update. ( #3459 )
...
* Change calculation of memory total to be more accurate, allocated is actually smaller than reserved.
* Update README.md install documentation for Intel GPUs.
2024-05-12 06:36:30 -04:00
comfyanonymous
43079b39cd
Fix lowvram issue with saving checkpoints.
...
The previous fix didn't cover the case where the model was loaded in
lowvram mode right before.
2024-05-12 06:13:45 -04:00
comfyanonymous
397b840846
No longer necessary.
2024-05-12 05:34:43 -04:00
comfyanonymous
ae31a1b885
Fix issue with lowvram mode breaking model saving.
2024-05-11 21:55:20 -04:00
Simon Lui
87e7b35146
Change torch.xpu to ipex.optimize, xpu device initialization and remove workaround for text node issue from older IPEX. ( #3388 )
2024-05-02 03:26:50 -04:00
comfyanonymous
982b8e2276
Fix some memory related issues.
2024-04-14 12:08:58 -04:00
comfyanonymous
d93e3f1991
Fix issue with controlnet models getting loaded multiple times.
2024-04-06 18:38:39 -04:00
comfyanonymous
cd0be2a31e
Fix some performance issues with weight loading and unloading.
...
Lower peak memory usage when changing model.
Fix case where model weights would be unloaded and reloaded.
2024-03-28 18:04:42 -04:00
comfyanonymous
af7900cd79
Optimize memory unload strategy for more optimized performance.
2024-03-24 02:36:30 -04:00
comfyanonymous
2db9fdbacc
Fix regression with model merging.
2024-03-20 13:56:12 -04:00
comfyanonymous
1681937288
Don't unload model weights for non weight patches.
2024-03-20 02:27:58 -04:00
comfyanonymous
7e04cdafc0
Lower memory usage for loras in lowvram mode at the cost of perf.
2024-03-13 20:07:27 -04:00
comfyanonymous
46e5a518c3
Change log levels.
...
Logging level now defaults to info. --verbose sets it to debug.
2024-03-11 13:54:56 -04:00
comfyanonymous
35d0fd9a5d
Replace prints with logging and add --verbose argument.
2024-03-10 12:14:23 -04:00
comfyanonymous
8726a79de9
Add some tesla pascal GPUs to the fp16 working but slower list.
2024-03-02 17:16:31 -05:00
comfyanonymous
f4e74ae786
Enable fp16 by default on mps.
2024-02-19 12:00:48 -05:00
comfyanonymous
cabdbc2529
Manual cast for bf16 on older GPUs.
2024-02-17 09:01:17 -05:00
comfyanonymous
b3c820556b
Make --force-fp32 disable loading models in bf16.
2024-02-16 23:01:54 -05:00
comfyanonymous
deebc95781
Stable Cascade Stage C.
2024-02-16 10:55:08 -05:00
comfyanonymous
a3ada6af3b
Small refactor of is_device_* functions.
2024-02-15 21:10:10 -05:00
comfyanonymous
1bbaf69344
Don't use is_bf16_supported to check for fp16 support.
2024-02-04 20:53:35 -05:00
comfyanonymous
5efb046482
Speed up SDXL on 16xx series with fp16 weights and manual cast.
2024-02-04 13:23:43 -05:00
comfyanonymous
32be22279f
Always use fp16 for the text encoders.
2024-02-02 10:02:49 -05:00
comfyanonymous
96232a0a45
Only auto enable bf16 VAE on nvidia GPUs that actually support it.
2024-01-15 03:10:22 -05:00
comfyanonymous
25ec26ff9c
Add argument to run the VAE on the CPU.
2023-12-30 05:49:07 -05:00
comfyanonymous
48d2b242ee
Load weights that can't be lowvramed to target device.
2023-12-28 21:41:10 -05:00
comfyanonymous
0baa3cc687
--disable-smart-memory now unloads everything like it did originally.
2023-12-23 04:25:06 -05:00
comfyanonymous
59e4fbf255
Greatly improve lowvram sampling speed by getting rid of accelerate.
...
Let me know if this breaks anything.
2023-12-22 14:38:45 -05:00
comfyanonymous
65ada00818
Add --deterministic option to make pytorch use deterministic algorithms.
2023-12-17 16:59:21 -05:00
comfyanonymous
45acae2d06
Add an option --fp16-unet to force using fp16 for the unet.
2023-12-11 18:36:29 -05:00
comfyanonymous
f64ac62540
Use faster manual cast for fp8 in unet.
2023-12-11 18:24:44 -05:00
comfyanonymous
58b39151a4
Switch text encoder to manual cast.
...
Use fp16 text encoder weights for CPU inference to lower memory usage.
2023-12-10 23:00:54 -05:00
comfyanonymous
260b25aef8
Disable non blocking on mps.
2023-12-10 01:30:35 -05:00
comfyanonymous
63349484b8
Make --gpu-only put intermediate values in GPU memory instead of cpu.
2023-12-08 02:35:45 -05:00
comfyanonymous
1f1ef695bb
Slightly faster lora applying.
2023-12-06 05:13:14 -05:00
comfyanonymous
dfa7737afb
Use .itemsize to get dtype size for fp8.
2023-12-04 11:52:06 -05:00
comfyanonymous
080f5f4e84
UNET weights can now be stored in fp8.
...
--fp8_e4m3fn-unet and --fp8_e5m2-unet are the two different formats
supported by pytorch.
2023-12-04 11:10:00 -05:00
comfyanonymous
c013b8e94c
Add some command line arguments to store text encoder weights in fp8.
...
Pytorch supports two variants of fp8:
--fp8_e4m3fn-text-enc (the one that seems to give better results)
--fp8_e5m2-text-enc
2023-11-17 02:56:59 -05:00
comfyanonymous
9f546f0cb3
Disable xformers when it can't load properly.
2023-11-13 12:31:10 -05:00
comfyanonymous
21ea9c3263
Allow different models to estimate memory usage differently.
2023-11-12 04:03:52 -05:00
comfyanonymous
7f861d49fd
Empty the cache when torch cache is more than 25% free mem.
2023-10-22 13:58:12 -04:00
comfyanonymous
daabf7fd3a
Add some Quadro cards to the list of cards with broken fp16.
2023-10-16 16:48:46 -04:00
comfyanonymous
db653f4908
Add a --bf16-unet to test running the unet in bf16.
2023-10-13 14:51:10 -04:00
comfyanonymous
728139a5b9
Refactor code so model can be a dtype other than fp32 or fp16.
2023-10-13 14:41:17 -04:00
comfyanonymous
494ddf7717
pytorch_attention_enabled can now return True when xformers is enabled.
2023-10-11 21:30:57 -04:00
comfyanonymous
18e4504de7
Pull some small changes from the other repo.
2023-10-11 20:38:48 -04:00
Simon Lui
47164eb065
Allow Intel GPUs to LoRA cast on GPU since it supports BF16 natively.
2023-09-22 21:11:27 -07:00
comfyanonymous
795f5b3163
Only do the cast on the device if the device supports it.
2023-09-20 17:52:41 -04:00
comfyanonymous
cdbbeb584d
Enable pytorch attention by default on xpu.
2023-09-17 04:09:19 -04:00
