47d73041afcd82fa279582f57083557e35199e1a551ba634cf54801596b04c02

README.md

@@ -48,7 +48,7 @@ You can run the smashed model with these steps:
 0. Check cuda, torch, packaging requirements are installed. For cuda, check with `nvcc --version` and install with `conda install nvidia/label/cuda-12.1.0::cuda`. For packaging and torch, run `pip install packaging torch`.
 1. Install the `pruna-engine` available [here](https://pypi.org/project/pruna-engine/) on Pypi. It might take 15 minutes to install.
     ```bash
-   pip install pruna-engine[gpu] --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.ngc.nvidia.com --extra-index-url https://prunaai.pythonanywhere.com/
+   pip install pruna-engine[gpu]==0.6.0 --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.ngc.nvidia.com --extra-index-url https://prunaai.pythonanywhere.com/
     ```
 3. Download the model files using one of these three options. 
    - Option 1 - Use command line interface (CLI):

config.json

@@ -1 +1 @@
-{"pruners": "None", "pruning_ratio": "None", "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.0, "compilers": "['step_caching', 'tiling', 'diffusers2']", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "batch_size": 1, "max_batch_size": 1, "image_height": 1024, "image_width": 1024, "version": "xl-1.0", "scheduler": "DDIM", "task": "txt2imgxl", "weight_name": "None", "model_name": "segmind/Segmind-Vega", "save_load_fn": "stable_fast"}
+{"pruners": "None", "pruning_ratio": 0.0, "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.01, "compilers": "['step_caching', 'tiling', 'diffusers2']", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "batch_size": 1, "max_batch_size": 1, "image_height": 1024, "image_width": 1024, "version": "xl-1.0", "scheduler": "DDIM", "task": "txt2imgxl", "model_name": "segmind/Segmind-Vega", "weight_name": "None", "save_load_fn": "stable_fast"}

model/smash_config.json

@@ -1 +1 @@
-{"api_key": "pruna_c4c77860c62a2965f6bc281841ee1d7bd3", "verify_url": "http://johnrachwan.pythonanywhere.com", "smash_config": {"pruners": "None", "pruning_ratio": "None", "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.0, "compilers": "['step_caching', 'tiling', 'diffusers2']", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "cache_dir": ".models/optimized_model", "batch_size": 1, "max_batch_size": 1, "image_height": 1024, "image_width": 1024, "version": "xl-1.0", "scheduler": "DDIM", "task": "txt2imgxl", "weight_name": "None", "model_name": "segmind/Segmind-Vega", "save_load_fn": "stable_fast"}}
+{"api_key": "pruna_c4c77860c62a2965f6bc281841ee1d7bd3", "verify_url": "http://johnrachwan.pythonanywhere.com", "smash_config": {"pruners": "None", "pruning_ratio": 0.0, "factorizers": "None", "quantizers": "None", "n_quantization_bits": 32, "output_deviation": 0.01, "compilers": "['step_caching', 'tiling', 'diffusers2']", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "cache_dir": ".models/optimized_model", "batch_size": 1, "max_batch_size": 1, "image_height": 1024, "image_width": 1024, "version": "xl-1.0", "scheduler": "DDIM", "task": "txt2imgxl", "model_name": "segmind/Segmind-Vega", "weight_name": "None", "save_load_fn": "stable_fast"}}