Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

A matching Triton is not available, some optimizations will not be enabled #26

Closed
sbuldan opened this issue Feb 22, 2024 · 2 comments
Closed

Comments

@sbuldan
Copy link

sbuldan commented Feb 22, 2024

I am on windows 10 with a rtx 3090
Installed triton manualy but not sure installed it in the right folder or correct version. I need some help here.

Running 1 job
Z:\SDZ\ai-toolkit\venv\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree._register_pytree_node(
Z:\SDZ\ai-toolkit\venv\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree.register_pytree_node(
A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "Z:\SDZ\ai-toolkit\venv\lib\site-packages\xformers_init
.py", line 55, in _is_triton_available
from xformers.triton.softmax import softmax as triton_softmax # noqa
File "Z:\SDZ\ai-toolkit\venv\lib\site-packages\xformers\triton\softmax.py", line 14, in
from xformers.triton.k_softmax import _softmax, _softmax_backward
File "Z:\SDZ\ai-toolkit\venv\lib\site-packages\xformers\triton\k_softmax.py", line 8, in
import triton.language as tl
ModuleNotFoundError: No module named 'triton.language'
Z:\SDZ\ai-toolkit\venv\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree._register_pytree_node(
Z:\SDZ\ai-toolkit\venv\lib\site-packages\diffusers\models\unet_2d_condition.py:20: FutureWarning: UNet2DConditionOutput is deprecated and will be removed in version 0.29. Importing UNet2DConditionOutput from diffusers.models.unet_2d_condition is deprecated and this will be removed in a future version. Please use from diffusers.models.unets.unet_2d_condition import UNet2DConditionOutput, instead.
deprecate("UNet2DConditionOutput", "0.29", deprecation_message)
Z:\SDZ\ai-toolkit\venv\lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch.utils._pytree._register_pytree_node(
Z:\SDZ\ai-toolkit\venv\lib\site-packages\diffusers\models\unet_2d_condition.py:25: FutureWarning: UNet2DConditionModel is deprecated and will be removed in version 0.29. Importing UNet2DConditionModel from diffusers.models.unet_2d_condition is deprecated and this will be removed in a future version. Please use from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel, instead.
deprecate("UNet2DConditionModel", "0.29", deprecation_message)
{
"type": "slider",
"network": {
"type": "lierla",
"linear": 8,
"linear_alpha": 4
},
"train": {
"noise_scheduler": "ddpm",
"steps": 500,
"lr": 0.0002,
"gradient_checkpointing": true,
"train_unet": true,
"train_text_encoder": false,
"min_snr_gamma": 5.0,
"optimizer": "adamw",
"lr_scheduler": "constant",
"max_denoising_steps": 40,
"batch_size": 1,
"dtype": "bf16",
"noise_offset": 0.0357
},
"model": {
"name_or_path": "./albedobaseXL_v21.safetensors",
"is_v2": false,
"is_v_pred": false,
"is_xl": false
},
"save": {
"dtype": "float16",
"save_every": 50,
"max_step_saves_to_keep": 2
},
"sample": {
"sampler": "ddpm",
"sample_every": 20,
"width": 512,
"height": 512,
"prompts": [
"a woman in a coffee shop, black hat, blonde hair, blue jacket --m -5",
"a woman in a coffee shop, black hat, blonde hair, blue jacket --m -3",
"a woman in a coffee shop, black hat, blonde hair, blue jacket --m 3"
],
"neg": "cartoon, fake, drawing, illustration, cgi, animated, anime, monochrome",
"seed": 42,
"walk_seed": false,
"guidance_scale": 7,
"sample_steps": 20,
"network_multiplier": 1.0
},
"logging": {
"log_every": 10,
"use_wandb": false,
"verbose": false
},
"slider": {
"resolutions": [
[
1024,
1024
]
],
"batch_full_slide": true,
"targets": [
{
"target_class": "",
"positive": "high detail, 8k, intricate, detailed, high resolution, high res, high quality",
"negative": "blurry, boring, fuzzy, low detail, low resolution, low res, low quality",
"weight": 1.0,
"shuffle": true
}
]
}
}
Building slider targets
Built 8 slider targets (with permutations)

#############################################

Running job: detail_slider_v1

#############################################

Running 1 process
Error running job: StableDiffusionPipeline.init() got an unexpected keyword argument 'tokenizer_2'

========================================
Result:

  • 0 completed jobs
  • 1 failure
    ========================================
    Traceback (most recent call last):
    File "Z:\SDZ\ai-toolkit\run.py", line 89, in
    main()
    File "Z:\SDZ\ai-toolkit\run.py", line 85, in main
    raise e
    File "Z:\SDZ\ai-toolkit\run.py", line 77, in main
    job.run()
    File "Z:\SDZ\ai-toolkit\jobs\TrainJob.py", line 49, in run
    process.run()
    File "Z:\SDZ\ai-toolkit\jobs\process\BaseSDTrainProcess.py", line 1075, in run
    self.sd.load_model()
    File "Z:\SDZ\ai-toolkit\toolkit\stable_diffusion_model.py", line 283, in load_model
    pipe = pipln.from_single_file(
    File "Z:\SDZ\ai-toolkit\venv\lib\site-packages\huggingface_hub\utils_validators.py", line 118, in _inner_fn
    return fn(*args, **kwargs)
    File "Z:\SDZ\ai-toolkit\venv\lib\site-packages\diffusers\loaders\single_file.py", line 274, in from_single_file
    pipe = pipeline_class(**init_kwargs)
    TypeError: StableDiffusionPipeline.init() got an unexpected keyword argument 'tokenizer_2'
@ItsAuver
Copy link

ItsAuver commented Apr 14, 2024

At the time of this comment, Triton has not been compiled/ported to Windows to the best of my knowledge. See triton-lang/triton#1640

@DarkAlchy
Copy link

It never will be the devs said last year. The best we have is just a wrapper around 500mb for 2.1 cuda.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants