github AlexsJones/llmfit v0.9.16

6 hours ago

0.9.16 (2026-04-27)

Features

  • add community benchmarks view from localmaxxing.com (4d0ffa7)
  • add hardware picker to benchmarks view (H key) (21661b2)
  • add vLLM inference provider (bfb0bb2), closes #501
  • download: add --output-dir flag to override cache path (#499) (f70409f)

Bug Fixes

  • add debug warning when util > 1.0 in GPU-mode VRAM pressure calculation (#513) (92d0f63), closes #496
  • deduplicate AMD GPUs detected by both ROCm and Vulkan (fixes #139) (#314) (43dd9fc)
  • match leaderboard API nested response schema (4282eb4)

What's Changed

  • feat(download): add --output-dir flag to override cache path by @mvanhorn in #499
  • fix: deduplicate AMD GPUs detected by both ROCm and Vulkan by @octo-patch in #314
  • Docs: Describe Python-based install options in the readme by @JEHoctor in #410
  • chore(deps): bump actions/cache from 5.0.3 to 5.0.5 by @dependabot[bot] in #510
  • fix: add debug warning when util > 1.0 in GPU-mode VRAM pressure by @octo-patch in #513
  • chore(main): release 0.9.16 by @AlexsJones in #507

Full Changelog: v0.9.15...v0.9.16

Don't miss a new llmfit release

NewReleases is sending notifications on new releases.