Skip to content

Build a matched-budget reasoning quality evaluation harness #6

Description

@DaBestCode

Measure whether random eviction preserves answer quality under controlled cache budgets. This is required before a performance-focused launch.

Acceptance criteria:

  • Add a CLI that evaluates dense and RandKV generation over the same immutable prompt set.
  • Start with one openly licensed, exact-match reasoning dataset and document its name, split, version/revision, and scoring normalization.
  • Record exact model revision, generation parameters, device, seed, budget, buffer, per-example outputs, and aggregate accuracy in machine-readable JSON.
  • Force identical prompt formatting and generation limits across modes.
  • Include a small local fixture so evaluator/scorer tests run offline in CI; the real dataset must not be downloaded in CI.
  • Keep evaluation dependencies optional and outside the core runtime install.
  • Report failures and invalid generations; never silently drop examples.

Please propose the initial dataset and output schema in a comment before implementation.

Activity

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

    area: evaluationBenchmarks, quality evaluation, and result artifactshelp wantedExtra attention is neededlaunch blockerRequired before performance-focused official launch

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions