Skip to content

Tensor Parallel profiling result #22

Closed
@zhuohan123

Description

@zhuohan123

Will update the profiling results in this PR.

BS=8, input_len=32, output_len=128

OPT-13B
TP 1: 3.5404738585154214 seconds
TP 2: 4.742188215255737 seconds
TP 4: 4.907034238179524 seconds

OPT-30B
TP 1: OOM
TP 2: 5.9848620891571045 seconds
TP 4: 5.943212985992432 seconds

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