Skip to content

GitLab

Explore

Sign in

Commits · fdbc770175ed1ebd315b4f7084f1d11079883d98

coderai
codai
api
h3_worker.py

Oct 29, 2026
- give an isolated worker the environment it needs, and a resident speech model room to run · 3d507226
  Stefy Lanza (nextime / spora ) authored Oct 29, 2026
  3d507226
Oct 24, 2026
- download HuggingFace models where the config says, in every process (v0.4.88) · c4539260
  Stefy Lanza (nextime / spora ) authored Oct 25, 2026
  c4539260
Sep 16, 2026
- speaker: pyannote needs matplotlib — and a venv check has to reach the real load · 57f72ea3
  Stefy Lanza (nextime / spora ) authored Sep 16, 2026
  57f72ea3
Sep 13, 2026
- workers: let every isolated-venv worker point at a remote service · 4766c1df
  Stefy Lanza (nextime / spora ) authored Sep 13, 2026
  4766c1df
- h3: run the newer diffusers as a 75 MB overlay, and train through it · 3d53da50
  Stefy Lanza (nextime / spora ) authored Sep 13, 2026
  3d53da50
Sep 10, 2026
- video: run MiniMax-H3 in the engine like any other model, worker as fallback · 14d45861
  Stefy Lanza (nextime / spora ) authored Sep 10, 2026
  14d45861
- video: serve MiniMax-H3 through an isolated worker, and clone voices in the studio · 4abca4a9
  Stefy Lanza (nextime / spora ) authored Sep 10, 2026
  4abca4a9

Loading