Re:Nvidia Dynamo: A Datacenter Scale Distributed Inference S...
by aabhay on Tuesday March 18, 2025 @07:47PM
(#43406645)
Triton is not that bad at all, considering the wide scope of systems it has to support (tensorrt, onnx, multiple generations of pytorch, cuda, python). It was much nicer than the old Torchserve project which was JVM based.
[ Parent
| on HN ]
There are no comments on this comment yet.