1. Add tuned vae model in the SD web.
2. Use tuned models in case of rdna3 cards.
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
1. Get the correct vulkan-target-triple for a specified device in the
presence of multiple cards.
2. Use tuned unet model for rdna3 cards.
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
-Adds date variable back to nightly.yml so shark_tank uploads are dated again
-added specification for nightly pytests to not run tests on metal (vulkan is sufficient)
-added some paths/filetypes to be ignored when triggering workflow runs. (no test-models on changes to .md files or anything in the shark/examples/ directory or its subdirectories.
-pytest only picks up tank/test_models.py, so no need to specify which file to run when running pytest from SHARK base directory.
-Cleaned up xfails so that they can be added to models as csv entries. Columns 7-9 in all_models.csv trigger xfails with cpu, cuda, vulkan, respectively, and row 10 can be populated with a reason for the xfails.
-Fixed a few defaults for shark_args and pytest args (defined in conftest.py)
-Fixes --update_tank option in shark_downloader
removes some multiprocessing in pytest / TF+CUDA support because it breaks pytest and false passes, leaving regressions at large.
-Adds xfails for and removes albert torch from gen_sharktank list (tank/torch_model_list.csv).
-Cleans up xfails for cpu, cuda, vulkan (removing old ones)
* Move most xfails to entries in tank/all_models.csv
* enable usage of pytest without specifying tank/test_models.py
* add dict_configs.py to gitignore.
* Pin versions for runtimes and torch-mlir for setup.
1. Update the models to 8 dec.
2. precision is default to `fp16` in CLI.
3. version is default to `v2.1base` in CLI as well as web.
4. The default scheduler is set to `EulerDiscrete` now.
Signed-Off-by: Gaurav Shukla <gaurav@nod-labs.com>
Signed-off-by: Gaurav Shukla <gaurav@nod-labs.com>
1. Add schedulers option in web UI.
2. Remove random seed checkbox as the same functionality can be achieved
by passing -1(or any negative number) to the seed.
Signed-Off-by: Gaurav Shukla
Signed-off-by: Gaurav Shukla
