search

AI-Hypercomputer / jetstream-pytorch

PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"
Apache License 2.0
41 stars 15 forks source link

Stacked cache for MLPerf #154

Closed wang2yn84 closed 4 months ago

wang2yn84 commented 4 months ago

Same as https://github.com/google/jetstream-pytorch/pull/151, check in to this branch for MLPerf