Closed EthanMarx closed 1 week ago
@wbenoit26 this is ready to take a look at - before it's merged, I want to do a little test run directly comparing TensorRT
and TorchScript
export
And you can also remove hermes
from the known_third_party
list
@wbenoit26 Added sample_rate
and kernel_length
as arguments to all models since the S4
requires this before runtime. These are linked from the data module via the cli
law
sideproject
to be compatible withTorchScript
hermes
as submoduleAFRAME_
env vars corresponding to directories so that users can point to one anothers filesWandbSaveConfig
callback8.5.2.2
to be compatible with triton23.01
There is a nasty memory leak in older triton containers
22.XX
when making multi-gpu inference requests with a model exported and hosted with libtorch backend (TorchScript). These went away in23.01
.@wbenoit26 Ready to look over. I snuck in a couple other fixes here, happy to strip them out into separate PRs if that's easier