Skip to content

GitLab

"docs/vscode:/vscode.git/clone" did not exist on "e86c414d6ac540166781f203b1ec48826aab9f7c"
Switch branch/tag
Find file BlameHistoryPermalink
  • SangBin Cho's avatar
    [Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode... · 65bf2ac1
    SangBin Cho authored 
    [Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API (#4681)

This PR combines prepare_prompt and prepare_decode into a single API. This PR also coelsce the attn metadata for prefill/decode to a single class and allow to slice them when running attn backend.

It also refactors subquery_start_loc which was not refactored in the previous PR
    65bf2ac1
multi_step_worker.py 8.32 KB