#focused #serverless #inference #engine #triton-based

yanked pumars

Triton-based inference engine focused on lightweight, high-performance for Serverless

1 unstable release

0.0.1 Sep 16, 2024

#53 in #focused

Apache-2.0

7KB

puma.rs

Triton-based inference engine focused on lightweight, high-performance for Serverless.

No runtime deps