You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
ValueError: model must be a torch.nn.Module, got <class.
'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'>
model=StableDiffusionPipeline.from_pretrained(
HF_MODEL_ID,
torch_dtype=torch.float16,
revision="fp16")
model=deepspeed.init_inference(model=model.to("cuda"), dtype=torch.float16)
model("a photo of an astronaut riding a horse on moon")
The text was updated successfully, but these errors were encountered:
File "/opt/conda/envs/deepspeed01/lib/python3.9/site-packages/deepspeed/ops/transformer/inference/diffusers_attention.py", line 81, in selfAttention_fp
context_layer = triton_flash_attn_kernel(qkv_out[0],
File "/opt/conda/envs/deepspeed01/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/conda/envs/deepspeed01/lib/python3.9/site-packages/deepspeed/ops/transformer/inference/triton_ops.py", line 119, in forward
_fwd_kernel[grid](
File "/opt/conda/envs/deepspeed01/lib/python3.9/site-packages/triton/runtime/jit.py", line 106, in launcher
return self.run(*args, grid=grid, **kwargs)
File "", line 43, in _fwd_kernel
RuntimeError: Triton Error [CUDA]: invalid argument
stevensu1977
changed the title
[BUG] deep inference get model must be a torch.nn.Module
[BUG] deep inference get Triton Error [CUDA]: invalid argument
Mar 4, 2023
stevensu1977
changed the title
[BUG] deep inference get Triton Error [CUDA]: invalid argument
[BUG] deep inference on T4 get Triton Error [CUDA]: invalid argument
Mar 4, 2023
I try deepspeed and ComVis origin txt2img.py , deepseed inference it's work , I think may be it's diffuserss pipeline issue , if anything that I missed please tell me , thanks !
May I missing something ?
env:
accelerate==0.16.0
deepspeed==0.7.4+fffca7df
diffusers==0.12.0
tokenizers==0.12.1
torch==1.11.0+cu113
torchvision==0.12.0+cu113
tqdm==4.65.0
transformers==4.26.1
error message:
ValueError: model must be a torch.nn.Module, got <class.
'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'>
The text was updated successfully, but these errors were encountered: