OpenPPL/ppl.llm.serving

Onnx Support

loretoparisi opened this issue · 1 comments

What are the problems?

Support ONNX format.

What are the types of GPU/CPU you are using?

Intel / Nvidia

What's the operating system ppl.llm.serving runs on?

Linux / Debian

What's the compiler and its version?

gcc 9.0

Which version(commit id or tag) of ppl.llm.serving is used?

latest

What are the commands used to build ppl.llm.serving?

What are the execution commands?

minimal code snippets for reproducing these problems(if necessary)

models and inputs for reproducing these problems (send them to openppl.ai@hotmail.com if necessary)

Please describe more info about your problem. I guess it is the problem of model model format. Please export model to pmx format using our tools: https://github.com/openppl-public/ppl.pmx