search

google / jetstream-pytorch

PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"
Apache License 2.0
33 stars 14 forks source link

Return np instead of jax array for prefill result tokens #158

Closed FanhaiLu1 closed 1 month ago

FanhaiLu1 commented 1 month ago

All the ray worker returned array should be np array.