Carlos Eduardo Fernández fernandez14
sayakpaul
/ inference_with_torchao_serialized.py
Last active
January 13, 2025 01:51
Shows how to run Flux schnell under 17GBs without bells and whistles. It additionally shows how to serialize the quantized checkpoint and load it back.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import torch | |
| from huggingface_hub import hf_hub_download | |
| from diffusers import FluxTransformer2DModel, DiffusionPipeline | |
| dtype, device = torch.bfloat16, "cuda" | |
| ckpt_id = "black-forest-labs/FLUX.1-schnell" | |
| with torch.device("meta"): | |
| config = FluxTransformer2DModel.load_config(ckpt_id, subfolder="transformer") | |
| model = FluxTransformer2DModel.from_config(config).to(dtype) |
bcambel
/ nginx.conf
Created
August 16, 2013 06:57
Nginx maintenance redirect when a specific file exists
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| server { | |
| listen 80; | |
| server_name mysite.com; | |
| root /var/www/mysite.com/; | |
| location / { | |
| if (-f $document_root/maintenance.html) { | |
| return 503; | |
| } | |
| ... # the rest of your config goes here |