ai-hypercomputer/jetstream
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). License: apache-2.0. Hugging Bay hosted release. Scan: pending.
- License
- apache-2.0
- Scan status
- pending
- Hosting status
- external
- Upstream
- AI-Hypercomputer/JetStream
Open interactive artifact page