You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Jetstream is a very performant solution for inference for TPUs. The idea is to use their Pytorch implementation and try to use it as backend for TGI.
If the solution is successful, it could eventually replace current optimum-tpu TGI, and the code might land directly as part of TGI.
Note that this will require the models obtained from #58.
The text was updated successfully, but these errors were encountered:
Jetstream is a very performant solution for inference for TPUs. The idea is to use their Pytorch implementation and try to use it as backend for TGI.
If the solution is successful, it could eventually replace current optimum-tpu TGI, and the code might land directly as part of TGI.
Note that this will require the models obtained from #58.
The text was updated successfully, but these errors were encountered: