AI-Hypercomputer/JetStream

Model Serving

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

GitHub Metrics

Stars

415

Forks

Open Issues

Watchers

Contributors

Weekly Commits

Language

Python

License

Apache-2.0

Last Commit

Jan 5, 2026

Created

Mar 1, 2024

Latest Release

v0.3

Release Date

Dec 18, 2024

Synced: Mar 3, 2026

Quality Scores

Documentation Qualityw: 20%

0.0

Community Healthw: 20%

0.0

Maintenance Velocityw: 15%

0.0

API Design & DXw: 20%

0.0

Production Readinessw: 15%

0.0

Ecosystem Integrationw: 10%

0.0