Stable diffusion WebGPU port (#1370)

* WIP: Stable diffusion WebGPU port

* Load whole model: split safetensor to avoid Chrome allocation limit

* Gitignore .DS_Store, remove debug print

* Clip tokenizer in JS

* WIP: Compile model in parts (text model, diffusor, get_x_prev_and_pred_x0, decoder), and recreate forward logic in JS

* e2e stable diffusion flow

* Create initial random latent tensor in JS

* SD working e2e

* Log if some weights were not loaded properly

* Remove latent_tensor.npy used for debugging

* Cleanup, remove useless logs

* Improve UI

* Add progress bar

* Remove .npy files used for debugging

* Add clip tokenizer as external dependency

* Remove alphas_cumprod.js and load it from safetensors

* Refactor

* Simplify a lot

* Dedup base when limiting elementwise merge (webgpu)

* Add return type to safe_load_metadata

* Do not allow run when webgpu is not supported

* Add progress bar, refactor, fix special names

* Add option to chose from local vs huggingface weights

* lowercase tinygrad :)

* fp16 model dl, decompression client side

* Cache f16 model in browser, better progress

* Cache miss recovery

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>

.gitignore

@@ -1,6 +1,7 @@
 __pycache__
 .venv/
 .vscode
+.DS_Store
 notebooks
 .*.swp
 .*.swo
@@ -31,7 +32,8 @@ extra/datasets/kits/
 extra/datasets/COCO/
 extra/datasets/audio*
 venv
-examples/net.*[js,json,safetensors]
+examples/**/net.*[js,json]
+examples/**/*.safetensors
 node_modules
 package.json
 package-lock.json