Skip to content

client-driven Ollama arm (apr test llm bench + client sha256) before any ratio vs Ollama #5033

Closed as not planned

Description

@noahgift

What

Add a client-driven Ollama arm (apr test llm bench plus a client-side sha256 of the output) before any ratio against Ollama is published.

Today the card row says "measured by us" for a number that is self-timed, and the beat-ollama contract ratio uses Ollama's own reported eval rate rather than a client-measured one.

Done when

Any Ollama ratio is computed from a client-driven run with the output sha256 recorded, and the card wording matches what was measured.

Proposed by la-0.72b (inbox 04:49Z, ticket context #4401). Refs #4401.

Activity

  1. added this to the 0.72.0 milestone on Oct 10, 2026
  2. noahgift commented on Oct 10, 2026

    @noahgift
    MemberAuthor

    Parked from #4381: the epic is at 10 open children against a budget of 9, after new tickets were linked. This ticket has no pushed branch and no open PR. It stays open, keeps its owner and milestone, and re-enters when a child of that epic closes (1-in-1-out). Nothing reads sub-issue membership (checked: no code, workflow or contract), so no gate changes.

  3. noahgift commented on Oct 14, 2026

    @noahgift
    MemberAuthor

    merged into #5305 (master ticket for epic #3598; triage rule 7b, 2026-10-14). It is a checklist row there; reopen this issue when work on it starts or its PR opens.

  4. noahgift commented on Oct 14, 2026

    @noahgift
    MemberAuthor

    Moved: this sub-ticket is now a row in #5322 (Speed measurement harness: resource receipts, observability and the ollama/llama.cpp ratio), split out of #5305 by theme.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    owner:la-0.72bagent owner (cop executor a3)

    Type

    No type

    Projects

    No projects

      Milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions