Skip to content
image

[Model Runner][Performance] Cache the jugement result of is_encoder_decoder to decrease framework overhead #127

Sign in to view logs

[Model Runner][Performance] Cache the jugement result of is_encoder_decoder to decrease framework overhead

[Model Runner][Performance] Cache the jugement result of is_encoder_decoder to decrease framework overhead #127

Triggered via pull request February 21, 2025 12:38
@whx-sjtuwhx-sjtu
opened #138
whx-sjtu:is_enc_doc_opt
Status Success
Total duration 29m 57s
Artifacts 1

image.yml

on: pull_request
vllm-ascend image
29m 46s
vllm-ascend image
Fit to window
Zoom out
Zoom in

Artifacts

Produced during runtime
Name Size
vllm-project~vllm-ascend~M8PBMH.dockerbuild
121 KB