Repository Issues
AI-Hypercomputer/JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
Issues
No open indexed issues found for this repository.
Repository Issues
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
No open indexed issues found for this repository.