Skip to content

Latest commit

 

History

History
23 lines (15 loc) · 1.67 KB

File metadata and controls

23 lines (15 loc) · 1.67 KB

Changelog

All notable changes to this project will be documented in this file.

v0.1.0 (2026-06-24)

Features

  • feat: new inference-perf evaluator plugin; uses a single workload and a single concurrency level (#5 by @diw-zw)
  • feat: add K8s scheduling options, image pull secrets, and dedicated m… (#11 by @diw-zw)
  • Early stop (#9 by @diw-zw)
  • Add workload type: conversation_replay; add sweep function (#10 by @diw-zw)

Bug Fixes

  • Fix: Handle genai-bench post-benchmark failures gracefully (#4 by @diw-zw)
  • Fix: incorrect search space type display in UI (#6 by @diw-zw)

Misc

  • refactor: Extract codebase from rbg repository and restructure as inference-ext-cli (#1 by @diw-zw)
  • misc: add vendor/ ; add pull_request_template.md, README.md (#2 by @diw-zw)
  • Update docker image (#14 by @diw-zw)