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 →

4.9

GitHub Metrics

Stars

442

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: Jun 3, 2026

Quality Scores

Documentation Qualityw: 20%

4.8

No dedicated docs site. Description: 143 chars. Stars signal: 442. Contributors: 38. Score: 4.8/10

Community Healthw: 20%

5.2

Stars: 442. Contributors: 38. Watchers: 23. Forks: 65. Issue ratio: 6.1%. Score: 5.2/10

Maintenance Velocityw: 15%

3.5

Last commit: 149d ago. Weekly commits: 0. Latest release: v0.3. Maturity bonus: 2.3y old. Score: 3.5/10

API Design & DXw: 20%

5.8

Stars/issues ratio: 16. Dynamic language: Python. No dedicated API docs. Permissive license: Apache-2.0. Popularity signal: 442 stars. Score: 5.8/10

Production Readinessw: 15%

4.2

Battle-tested: 442 stars. Peer review: 38 contributors. Versioned: v0.3. Licensed: Apache-2.0. Age: 2.3 years. Maintenance: last commit 149d ago. Score: 4.2/10

Ecosystem Integrationw: 10%

6.1

Fork interest: 65. Major ecosystem: Python. Integration-friendly: Apache-2.0. Adoption: 442 stars. Score: 6.1/10