github jundot/omlx v0.2.20.dev2

latest releases: v0.3.9.dev1, v0.3.8, v0.3.8rc1...
pre-releaseone month ago

This is a pre-release build for testing purposes.

New Features

  • Hybrid quantization modes — per-layer mxfp4/mxfp8/affine format selection for better quality-size tradeoffs
  • Clip optimization speedup — GPU batch size setting for faster AWQ-style clipping
  • Block inference during quantization — prevents request conflicts while oQ is running
  • Download raw results — export benchmark results as JSON
  • Use model sampling settings — benchmarks now respect per-model sampling parameters

Bug Fixes

  • fix MC benchmarks (MMLU, HellaSwag, TruthfulQA) always scoring 0%

Don't miss a new omlx release

NewReleases is sending notifications on new releases.