Why can't the tensorrt engine I generated in cuda:0 be used in cuda:1?

[vxiaobai]

Why can't the tensorrt engine I generated in cuda:0 be used in cuda:1?
`Activating unet: [TRT] sd_xl_base_1.0
Loading TensorRT engine: /app/stable-diffusion-webui/models/Unet-trt/sd_xl_base_1.0_be9edd61_cc80_sample=1x4x96x96+2x4x128x128+8x4x128x128-timesteps=1+2+8-encoder_hidden_states=1x77x2048+2x77x2048+8x154x2048-y=1x2816+2x2816+8x2816.trt

Loaded Profile: 0
sample = [(1, 4, 96, 96), (2, 4, 128, 128), (8, 4, 128, 128)]
timesteps = [(1,), (2,), (8,)]
encoder_hidden_states = [(1, 77, 2048), (2, 77, 2048), (8, 154, 2048)]
y = [(1, 2816), (2, 2816), (8, 2816)]
latent = [(0), (0), (0)]

0%| | 0/40 [00:00<?, ?it/s][W] 'colored' module is not installed, will not use colors when logging. To enable colors, please install the 'colored' module: python3 -m pip install colored
[E] 1: [convBaseRunner.cpp::execute::319] Error Code 1: Cask (Cask convolution execution)
0%| | 0/40 [00:07<?, ?it/s]
*** Error completing request
*** Arguments: ('task(jj69p8cz7gmlcr4)', <gradio.routes.Request object at 0x7f6c4c13a290>, 'lora:LogoRedmondv2:1,logo, sports car, dreamlike', 'low quality, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry', [], 1, 4, 7, 1024, 1024, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', 'Use same scheduler', '', '', [], 0, 40, 'DPM++ 2M', 'Automatic', False, '', 0.8, -1, False, -1, 0, 0, 0, ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, union_control_type=<ControlNetUnionControlType.UNKNOWN: 'Unknown'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[], batch_keyframe_idx=None), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, union_control_type=<ControlNetUnionControlType.UNKNOWN: 'Unknown'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[], batch_keyframe_idx=None), ControlNetUnit(is_ui=True, input_mode=<InputMode.SIMPLE: 'simple'>, batch_images='', output_dir='', loopback=False, enabled=False, module='none', model='None', weight=1.0, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, low_vram=False, processor_res=-1, threshold_a=-1.0, threshold_b=-1.0, guidance_start=0.0, guidance_end=1.0, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, inpaint_crop_input_image=False, hr_option=<HiResFixOption.BOTH: 'Both'>, save_detected_map=True, advanced_weighting=None, effective_region_mask=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, union_control_type=<ControlNetUnionControlType.UNKNOWN: 'Unknown'>, ipadapter_input=None, mask=None, batch_mask_dir=None, animatediff_batch=False, batch_modifiers=[], batch_image_files=[], batch_keyframe_idx=None), False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, False, False, False, 0, False, None, None, False, None, None, False, None, None, False, 50) {}
Traceback (most recent call last):
File "/app/stable-diffusion-webui/modules/call_queue.py", line 74, in f
res = list(func(*args, **kwargs))
File "/app/stable-diffusion-webui/modules/call_queue.py", line 53, in f
res = func(*args, **kwargs)
File "/app/stable-diffusion-webui/modules/call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "/app/stable-diffusion-webui/modules/txt2img.py", line 109, in txt2img
processed = processing.process_images(p)
File "/app/stable-diffusion-webui/modules/processing.py", line 847, in process_images
res = process_images_inner(p)
File "/app/stable-diffusion-webui/extensions/sd-webui-controlnet/scripts/batch_hijack.py", line 59, in processing_process_images_hijack
return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
File "/app/stable-diffusion-webui/modules/processing.py", line 988, in process_images_inner
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
File "/app/stable-diffusion-webui/modules/processing.py", line 1346, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
File "/app/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 230, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "/app/stable-diffusion-webui/modules/sd_samplers_common.py", line 272, in launch_sampling
return func()
File "/app/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 230, in
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
File "/app/miniconda3/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/app/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/sampling.py", line 594, in sample_dpmpp_2m
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "/app/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/app/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/app/stable-diffusion-webui/modules/sd_samplers_cfg_denoiser.py", line 249, in forward
x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict(cond_in, image_cond_in))
File "/app/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/app/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/app/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 112, in forward
eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
File "/app/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 138, in get_eps
return self.inner_model.apply_model(*args, **kwargs)
File "/app/stable-diffusion-webui/modules/sd_models_xl.py", line 43, in apply_model
return self.model(x, t, cond)
File "/app/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/app/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1568, in _call_impl
result = forward_call(*args, **kwargs)
File "/app/stable-diffusion-webui/modules/sd_hijack_utils.py", line 22, in
setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
File "/app/stable-diffusion-webui/modules/sd_hijack_utils.py", line 34, in call
return self.__sub_func(self.__orig_func, *args, **kwargs)
File "/app/stable-diffusion-webui/modules/sd_hijack_unet.py", line 50, in apply_model
result = orig_func(self, x_noisy.to(devices.dtype_unet), t.to(devices.dtype_unet), cond, **kwargs)
File "/app/stable-diffusion-webui/repositories/generative-models/sgm/modules/diffusionmodules/wrappers.py", line 28, in forward
return self.diffusion_model(
File "/app/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/app/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "/app/stable-diffusion-webui/modules/sd_unet.py", line 89, in UNetModel_forward
return current_unet.forward(x, timesteps, context, *args, **kwargs)
File "/app/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/scripts/trt.py", line 72, in forward
out = self.engine.infer(feed_dict, self.cudaStream)["latent"]
File "/app/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/utilities.py", line 320, in infer
raise ValueError("ERROR: inference failed.")
ValueError: ERROR: inference failed.`

[T9es]

You using the same GPU type? From what I recall, you CAN'T use the same engine for a gpu that is from some other class.

If you are using the same tier gpu (Eg. Rtx 3090 in slot 0 and another 3090 in slot 1), you should be able to use the same engine from what I recall reading some other issues a few months back.