Skip to content

MLX-based experimental inference engine

active 2026-05-182026-08-10 (UTC)

Partial coverage12,327 / 14,034 hourly files (88%) · 2 absent upstream · 1,701 failed, retryable2025-01-032026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
821
Pushes
320
Pull requests
78
Issues
101
Stars
3
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 85 days from 2026-05-18 to 2026-08-10. Pushes: 320 total, peak 21 in a day. Pull requests: 78 total, peak 15 in a day. Issues: 101 total, peak 15 in a day. Comments: 8 total, peak 4 in a day. Stars: 3 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
inureyes499319738
dependabot[bot]6150
ujwal-setlur2000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#1083inureyes2026-08-07 21:09
    feat(server): serve Florence-2 through a seq2seq worker loop
  • Pull request#1083inureyes2026-08-07 20:48
  • Pull request#1083inureyes2026-08-07 20:48
  • Pull request#1083inureyes2026-08-07 20:48
  • Issue comment#1082inureyes2026-08-07 19:11
    feat(models): support quantized Florence-2 checkpoints (4-bit / 8-bit / 6-bit / 3-bit)
  • Pull request#1082inureyes2026-08-07 18:38
  • Pull request#1082inureyes2026-08-07 18:38
  • Pull request#1082inureyes2026-08-07 18:38
  • Pull request#1081inureyes2026-08-07 17:56
  • Pull request#1081inureyes2026-08-07 17:56
  • Issue#1072inureyes2026-08-07 17:49
    feat(models): support quantized Florence-2 checkpoints (4-bit / 8-bit / 6-bit / 3-bit)
  • Issue#849inureyes2026-08-07 17:34
    feat(models): add Jina VLM (jina_vlm) VLM support
  • Issue#849inureyes2026-08-07 17:34
    feat(models): add Jina VLM (jina_vlm) VLM support
  • Issue#849inureyes2026-08-07 17:34
    feat(models): add Jina VLM (jina_vlm) VLM support
  • Issue comment#1076inureyes2026-08-07 17:15
    feat(models): add Jina VLM (jvlm) vision-language support
  • Pull request#1076inureyes2026-08-07 17:15
  • Pull request#1076inureyes2026-08-07 17:15
  • Issue comment#1073inureyes2026-08-07 16:37
    feat(server): serve Florence-2 through a seq2seq worker loop
  • Pull request#1078inureyes2026-08-07 16:36
  • Pull request#1078inureyes2026-08-07 16:34
  • Pull request#1078inureyes2026-08-07 16:34
  • Pull request#1080inureyes2026-08-07 16:23
  • Pull request#1080inureyes2026-08-07 16:21
  • Issue#1079inureyes2026-08-07 16:20
    fix(test): two autotune tests decide on microsecond thread::sleep accuracy and flake under host load
  • Issue#830inureyes2026-08-05 04:14
    chore(deps): report the CUDA RMSNorm small-axis regression upstream and drop the local overlay once fixed

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 3 stars here means stars gained during the window, not the repo's star count.