Skip to content
This repository was archived by the owner on Jun 17, 2024. It is now read-only.
This repository was archived by the owner on Jun 17, 2024. It is now read-only.

Support for nvidia Triton Inference Server in ACI #42

@tom-r-o

Description

@tom-r-o

Running Triton on ACI (with a V100 GPU) yields errors in Triton:

ERROR: This container was built for NVIDIA Driver Release 450.51 or later, but
       version 410.104 was detected and compatibility mode is UNAVAILABLE.

       [[CUDA Driver UNAVAILABLE (cuInit(0) returned 803)]]

Running the same Triton image on an Azure VM with a V100 GPU from nvidia's image does not cause the error. I'm guessing this is related to some missing drivers.

Triton's quickstart guide is available here

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions