google-jetstream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
Activity
- Latest release
- 2y ago
- Total releases
- 4
- Cadence
- ~28 days
- Last 12 months
- 0
Details
- License
- Apache-2.0
- First release
- Mar 01, 2024
Releases
| Version | Released | |
|---|---|---|
0.2.2
patch
| ||
0.2.1
patch
| ||
0.2.0
minor
| ||
0.1.1
initial
|