Lincoln Stein 00e4652d30 add more reliable fallback method for determining BnbQuantizedLlmInt8b

2024-09-03 15:55:51 -04:00

..

load

[MM] add API routes for getting & setting MM cache sizes (#6523)

2024-09-02 12:18:21 -04:00

metadata

Apply ruff rule to disallow all relative imports.

2024-07-04 09:35:37 -04:00

util

Install sub directories with folders correctly, ensure consistent dtype of tensors in flux pipeline and vae

2024-08-26 20:17:50 -04:00

__init__.py

Apply ruff rule to disallow all relative imports.

2024-07-04 09:35:37 -04:00

config.py

Update t5 encoder formats to accurately reflect the quantization strategy and data type

2024-08-26 20:17:50 -04:00

merge.py

Apply ruff rule to disallow all relative imports.

2024-07-04 09:35:37 -04:00

probe.py

add more reliable fallback method for determining BnbQuantizedLlmInt8b

2024-09-03 15:55:51 -04:00

search.py

docs(mm): update ModelSearch

2024-03-28 12:35:41 +11:00

starter_models.py

Update starter model size estimates.

2024-08-26 20:17:50 -04:00