FreeAIRepo
Inference & serving

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).

Really freeApache-2.0Python
Stars
470
Forks
70
Open issues
14
Last push
9mo ago

About JetStream

JetStream is a free, open-source AI inference tool by AI-Hypercomputer, written mainly in Python. JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome). It has 470 GitHub stars and 70 forks, and was last updated 9mo ago. It's released under the Apache-2.0 license, a standard open-source license.

License
Apache-2.0
Language
Python
Stars
470
Last update
9mo ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not required
Self-hostable
Not stated

Similar free tools

All Inference & serving tools →

JetStream FAQ

Is JetStream free?

Yes. JetStream is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.

Does JetStream run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does JetStream need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is JetStream still maintained?

It was last updated 9mo ago. Check recent issues on GitHub to judge how active it is.

What are alternatives to JetStream?

Similar free, open-source tools include vllm, TensorRT-LLM, llama-cookbook, BentoML.

Related topics