kijai 17d964aa37 Support CublasOps for decoding ...

https://github.com/aredden/torch-cublas-hgemm

on a 4090 this is ~25% faster

2025-02-04 16:28:35 +02:00

..

models

Support CublasOps for decoding

2025-02-04 16:28:35 +02:00

__init__.py

init

2025-01-21 20:01:16 +02:00

pipelines.py

Support CublasOps for decoding

2025-02-04 16:28:35 +02:00

postprocessors.py

update

2025-01-21 23:40:10 +02:00

preprocessors.py

init

2025-01-21 20:01:16 +02:00

schedulers.py

init

2025-01-21 20:01:16 +02:00