Skip to content

[Inference PagedAttention] Integrate initial paged attention implementation into maxengine (2/N) #1686

[Inference PagedAttention] Integrate initial paged attention implementation into maxengine (2/N)

[Inference PagedAttention] Integrate initial paged attention implementation into maxengine (2/N) #1686

Triggered via pull request March 5, 2025 18:11
Status Success
Total duration 25m 55s
Artifacts

RunTests.yml

on: pull_request
gpu_image  /  Build and upload image (a100-40gb-4)
43s
gpu_image / Build and upload image (a100-40gb-4)
tpu_image  /  Build and upload image (v4-8)
4m 34s
tpu_image / Build and upload image (v4-8)
Clean up
7s
Clean up
Notify failed build
4s
Notify failed build
Fit to window
Zoom out
Zoom in