Skip to content
CI - sharktank perplexity short

Implement PageAllocation as a handle into a PagedAttentionCache, allowing publishing and releasing an allocation via handle rather than cache #163

Sign in to view logs

Implement PageAllocation as a handle into a PagedAttentionCache, allowing publishing and releasing an allocation via handle rather than cache

Implement PageAllocation as a handle into a PagedAttentionCache, allowing publishing and releasing an allocation via handle rather than cache #163

Triggered via pull request November 28, 2024 01:23
@renxidarenxida
synchronize #608
renxida:page-allocation-handle
Status Success
Total duration 3m 42s
Artifacts –

ci_eval_short.yaml

on: pull_request
Matrix: Llama3.1 8B FP16
Fit to window
Zoom out
Zoom in