Fix

Author: co63oc

demo/BERT/notebooks/README.md

@@ -1,6 +1,6 @@
 # TensorRT Demo with BERT
 
-To run the demo Jupyter notebooks in this folder, follow the instructions in the [TRT setup guide](../../../README.md) to build and launch the docker container. Then, use your browswer to open the Jupyter lab interface at <host_name>:8888/lab using the password provided in the terminal.
+To run the demo Jupyter notebooks in this folder, follow the instructions in the [TRT setup guide](../../../README.md) to build and launch the docker container. Then, use your browser to open the Jupyter lab interface at <host_name>:8888/lab using the password provided in the terminal.
 
 
 Notebook list:

demo/Diffusion/README.md

@@ -13,7 +13,7 @@ cd TensorRT
 
 ### Launch NVIDIA pytorch container
 
-Install nvidia-docker using [these intructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#docker).
+Install nvidia-docker using [these instructions](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#docker).
 
 ```bash
 docker run --rm -it --gpus all -v $PWD:/workspace nvcr.io/nvidia/pytorch:25.01-py3 /bin/bash
@@ -427,7 +427,7 @@ python3 demo_txt2img_flux.py "a beautiful photograph of Mt. Fuji during cherry b
 
 ## Configuration options
 - Noise scheduler can be set using `--scheduler <scheduler>`. Note: not all schedulers are available for every version.
-- To accelerate engine building time use `--timing-cache <path to cache file>`. The cache file will be created if it does not already exist. Note that performance may degrade if cache files are used across multiple GPU targets. It is recommended to use timing caches only during development. To achieve the best perfromance in deployment, please build engines without timing cache.
+- To accelerate engine building time use `--timing-cache <path to cache file>`. The cache file will be created if it does not already exist. Note that performance may degrade if cache files are used across multiple GPU targets. It is recommended to use timing caches only during development. To achieve the best performance in deployment, please build engines without timing cache.
 - Specify new directories for storing onnx and engine files when switching between versions, LoRAs, ControlNets, etc. This can be done using `--onnx-dir <new onnx dir>` and `--engine-dir <new engine dir>`.
 - Inference performance can be improved by enabling [CUDA graphs](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#cuda-graphs) using `--use-cuda-graph`. Enabling CUDA graphs requires fixed input shapes, so this flag must be combined with `--build-static-batch` and cannot be combined with `--build-dynamic-shape`.
 

demo/Diffusion/demo_controlnet.py

@@ -93,7 +93,7 @@ def parseArgs():
                 seg_image = controlnet_aux.SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")(seg_image)
                 input_images.append(seg_image.resize((args.height, args.width)))
             else:
-                raise ValueError(f"You should implement the conditonal image of this controlnet: {controlnet}")
+                raise ValueError(f"You should implement the conditional image of this controlnet: {controlnet}")
     assert len(input_images) > 0
 
     kwargs_init_pipeline, kwargs_load_engine, args_run_demo = process_pipeline_args(args)

demo/Diffusion/stable_diffusion_pipeline.py

@@ -896,9 +896,9 @@ def infer(
             image_strength (float):
                 Strength of transformation applied to input_image. Must be between 0 and 1.
             mask_image (image):
-                Mask image containg the region to be inpainted.
+                Mask image containing the region to be inpainted.
             controlnet_scales (torch.Tensor)
-                A tensor which containes ControlNet scales, essential for multi ControlNet.
+                A tensor which contains ControlNet scales, essential for multi ControlNet.
                 Must be equal to number of Controlnets.
             warmup (bool):
                 Indicate if this is a warmup run.

demo/Diffusion/stable_video_diffusion_pipeline.py

@@ -669,7 +669,7 @@ def __exit__(ctx, exc_type, exc_val, exc_tb):
                     latent_model_input = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                     latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
 
-                    # Concatenate image_latents over channels dimention
+                    # Concatenate image_latents over channels dimension
                     latent_model_input = torch.cat([latent_model_input, image_latents], dim=2)
 
                     # predict the noise residual