JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
AI-Hypercomputer/JetStream
View on GitHub ↗JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
JetStream grew +2.2% in the last 30 days, ranks 126th of 320 in Production Serving & Deployment, last commit 292 days ago.
Star trajectory
115 days tracked2026-07-02470 stars today2026-10-25
Momentum
+2.2% in 30d, above the Production Serving & Deployment median of +1.2%.
Maintenance
Last commit 292 days ago, staler than the median of 3d.
How it compares in Production Serving & Deployment
JetStream
470
stars
+2.2% 30d
commit 292 days ago
Production Serving & Deployment median
313
stars
+1.2% 30d
commit ~3d ago
Leader · vllm
95.4k
stars
+3.0% 30d
commit today
Ranked 126th of 320 by stars.
flytohub/flyto-core484-14hpcaitech/SwiftInfer473-3
AI-Hypercomputer/JetStream470
VecSzn/PolyStrata469+1strands-agents/box468+2- Language
- Python
- License
- Apache License 2.0
- Contributors
- 38
- Forks
- 70
- Watchers
- 22
- Open issues
- 14
- Releases
- 4
- Created
- 2024-03-01
- Stars this week
- +0
You've seen where JetStream stands today.
Get the moves before everyone else: the 5 Production Serving & Deployment repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.