Gradient says Parallax shards models into contiguous layer slices across heterogeneous machines and can route requests across a host, LAN or public internet. These capabilities were not independently benchmarked in this review.
Supported
Project announcement
Evidence (2): 2 supporting
- supports: Gradient
When a model is too big for one host, it is sharded into contiguous layer slices and distributed across your laptop, a lab GPU, and a teammate’s workstation, all orchestrated as one service.
- supports: Gradient
Each request takes the fastest path on a single host, across a LAN, or over the public internet, without a public IP or matching hardware.