Skip to content

【Inference Optimize】Optimize the repeated calculation part in the DSK attention layer and optimize the performance under mixed batch. #2061

【Inference Optimize】Optimize the repeated calculation part in the DSK attention layer and optimize the performance under mixed batch.

【Inference Optimize】Optimize the repeated calculation part in the DSK attention layer and optimize the performance under mixed batch. #2061

Triggered via pull request August 11, 2025 10:45
Status Success
Total duration 6s
Artifacts

ci.yml

on: pull_request
Fit to window
Zoom out
Zoom in