Triton CLI is an open source command line interface that enables users to create, deploy, and profile models served by the Triton Inference Server.
48
stars
2
forks
source link
Fix --prompt for different shapes, ignore onnx files on HF download, conditional import #25
Closed
rmccorm4 closed 8 months ago
Fixes to run
triton model infer -m gpt --prompt hello
locally