JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
(451 star) (67 fork) (0 issue indicizzate) (0 good first issue aperte)
Repository
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
A simple, performant, and scalable Jax LLM!